Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Chng Eng Siong
@article{DBLP:journals/taslp/HuCZC24, author = {Yuchen Hu and Chen Chen and Qiushi Zhu and Eng Siong Chng}, title = {Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust {ASR}}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {32}, pages = {1145--1156}, year = {2024}, url = {https://doi.org/10.1109/TASLP.2023.3332545}, doi = {10.1109/TASLP.2023.3332545}, timestamp = {Thu, 29 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/HuCZC24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/SunYGYC24, author = {Linhui Sun and Shuo Yuan and Aifei Gong and Lei Ye and Eng Siong Chng}, title = {Dual-Branch Modeling Based on State-Space Model for Speech Enhancement}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {32}, pages = {1457--1467}, year = {2024}, url = {https://doi.org/10.1109/TASLP.2024.3362691}, doi = {10.1109/TASLP.2024.3362691}, timestamp = {Thu, 29 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/SunYGYC24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-03473, author = {He Wang and Pengcheng Guo and Yue Li and Ao Zhang and Jiayao Sun and Lei Xie and Wei Chen and Pan Zhou and Hui Bu and Xin Xu and Binbin Zhang and Zhuo Chen and Jian Wu and Longbiao Wang and Eng Siong Chng and Sun Li}, title = {{ICMC-ASR:} The {ICASSP} 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge}, journal = {CoRR}, volume = {abs/2401.03473}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.03473}, doi = {10.48550/ARXIV.2401.03473}, eprinttype = {arXiv}, eprint = {2401.03473}, timestamp = {Wed, 24 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-03473.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-05746, author = {Heqing Zou and Meng Shen and Yuchen Hu and Chen Chen and Eng Siong Chng and Deepu Rajan}, title = {Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection}, journal = {CoRR}, volume = {abs/2401.05746}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.05746}, doi = {10.48550/ARXIV.2401.05746}, eprinttype = {arXiv}, eprint = {2401.05746}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-05746.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-10446, author = {Yuchen Hu and Chen Chen and Chao{-}Han Huck Yang and Ruizhe Li and Chao Zhang and Pin{-}Yu Chen and Eng Siong Chng}, title = {Large Language Models are Efficient Learners of Noise-Robust Speech Recognition}, journal = {CoRR}, volume = {abs/2401.10446}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.10446}, doi = {10.48550/ARXIV.2401.10446}, eprinttype = {arXiv}, eprint = {2401.10446}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-10446.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-05457, author = {Chen Chen and Ruizhe Li and Yuchen Hu and Sabato Marco Siniscalchi and Pin{-}Yu Chen and Eng Siong Chng and Chao{-}Han Huck Yang}, title = {It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition}, journal = {CoRR}, volume = {abs/2402.05457}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.05457}, doi = {10.48550/ARXIV.2402.05457}, eprinttype = {arXiv}, eprint = {2402.05457}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-05457.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-06894, author = {Yuchen Hu and Chen Chen and Chao{-}Han Huck Yang and Ruizhe Li and Dong Zhang and Zhehuai Chen and Eng Siong Chng}, title = {GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators}, journal = {CoRR}, volume = {abs/2402.06894}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.06894}, doi = {10.48550/ARXIV.2402.06894}, eprinttype = {arXiv}, eprint = {2402.06894}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-06894.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-10642, author = {Xiangyu Zhang and Daijiao Liu and Hexin Liu and Qiquan Zhang and Hanyu Meng and Leibny Paola Garcia and Eng Siong Chng and Lina Yao}, title = {Speaking in Wavelet Domain: {A} Simple and Efficient Approach to Speed up Speech Diffusion Model}, journal = {CoRR}, volume = {abs/2402.10642}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.10642}, doi = {10.48550/ARXIV.2402.10642}, eprinttype = {arXiv}, eprint = {2402.10642}, timestamp = {Fri, 22 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-10642.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/ChenHZZZC23, author = {Chen Chen and Yuchen Hu and Qiang Zhang and Heqing Zou and Beier Zhu and Eng Siong Chng}, editor = {Brian Williams and Yiling Chen and Jennifer Neville}, title = {Leveraging Modality-Specific Representations for Audio-Visual Speech Recognition via Reinforcement Learning}, booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI} 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February 7-14, 2023}, pages = {12607--12615}, publisher = {{AAAI} Press}, year = {2023}, url = {https://doi.org/10.1609/aaai.v37i11.26484}, doi = {10.1609/AAAI.V37I11.26484}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aaai/ChenHZZZC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aciids/LiuHC23, author = {Changsong Liu and Thi{-}Nga Ho and Eng Siong Chng}, editor = {Ngoc Thanh Nguyen and Siridech Boonsang and Hamido Fujita and Bogumila Hnatkowska and Tzung{-}Pei Hong and Kitsuchart Pasupa and Ali Selamat}, title = {An Empirical Study on Punctuation Restoration for English, Mandarin, and Code-Switching Speech}, booktitle = {Intelligent Information and Database Systems - 15th Asian Conference, {ACIIDS} 2023, Phuket, Thailand, July 24-26, 2023, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {13996}, pages = {286--296}, publisher = {Springer}, year = {2023}, url = {https://doi.org/10.1007/978-981-99-5837-5\_24}, doi = {10.1007/978-981-99-5837-5\_24}, timestamp = {Sun, 10 Sep 2023 08:54:56 +0200}, biburl = {https://dblp.org/rec/conf/aciids/LiuHC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aciids/PrachasereeGHPTCC23, author = {Chaiyasait Prachaseree and Kshitij Gupta and Thi{-}Nga Ho and Yizhou Peng and Kyaw Zin Tun and Eng Siong Chng and G. S. S. Chalapthi}, editor = {Ngoc Thanh Nguyen and Siridech Boonsang and Hamido Fujita and Bogumila Hnatkowska and Tzung{-}Pei Hong and Kitsuchart Pasupa and Ali Selamat}, title = {Adapting Code-Switching Language Models with Statistical-Based Text Augmentation}, booktitle = {Intelligent Information and Database Systems - 15th Asian Conference, {ACIIDS} 2023, Phuket, Thailand, July 24-26, 2023, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {13996}, pages = {310--322}, publisher = {Springer}, year = {2023}, url = {https://doi.org/10.1007/978-981-99-5837-5\_26}, doi = {10.1007/978-981-99-5837-5\_26}, timestamp = {Sun, 10 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aciids/PrachasereeGHPTCC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/acl/ZouSCHRC23, author = {Heqing Zou and Meng Shen and Chen Chen and Yuchen Hu and Deepu Rajan and Eng Siong Chng}, editor = {Anna Rogers and Jordan L. Boyd{-}Graber and Naoaki Okazaki}, title = {UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning}, booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023, Toronto, Canada, July 9-14, 2023}, pages = {659--672}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://doi.org/10.18653/v1/2023.findings-acl.41}, doi = {10.18653/V1/2023.FINDINGS-ACL.41}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/acl/ZouSCHRC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/acl/HuCLZC23, author = {Yuchen Hu and Chen Chen and Ruizhe Li and Heqing Zou and Eng Siong Chng}, editor = {Anna Rogers and Jordan L. Boyd{-}Graber and Naoaki Okazaki}, title = {{MIR-GAN:} Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition}, booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada, July 9-14, 2023}, pages = {11610--11625}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://doi.org/10.18653/v1/2023.acl-long.649}, doi = {10.18653/V1/2023.ACL-LONG.649}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/acl/HuCLZC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/acl/HuLCQZC23, author = {Yuchen Hu and Ruizhe Li and Chen Chen and Chengwei Qin and Qiu{-}Shi Zhu and Eng Siong Chng}, editor = {Anna Rogers and Jordan L. Boyd{-}Graber and Naoaki Okazaki}, title = {Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition}, booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), {ACL} 2023, Toronto, Canada, July 9-14, 2023}, pages = {15213--15232}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://doi.org/10.18653/v1/2023.acl-long.848}, doi = {10.18653/V1/2023.ACL-LONG.848}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/acl/HuLCQZC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/JiangHC23, author = {Yufei Jiang and Thi{-}Nga Ho and Eng Siong Chng}, title = {Adopting Neural Translation Model in Data Generation for Inverse Text Normalization}, booktitle = {Asia Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2023, Taipei, Taiwan, October 31 - Nov. 3, 2023}, pages = {38--45}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/APSIPAASC58517.2023.10317241}, doi = {10.1109/APSIPAASC58517.2023.10317241}, timestamp = {Sat, 02 Dec 2023 14:05:45 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/JiangHC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/MabenGCCS23, author = {Leander Melroy Maben and Zixun Guo and Chen Chen and Utkarsh Chudiwal and Chng Eng Siong}, title = {Study of Generative Adversarial Networks for Noisy Speech Simulation from Clean Speech}, booktitle = {Asia Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2023, Taipei, Taiwan, October 31 - Nov. 3, 2023}, pages = {1143--1149}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/APSIPAASC58517.2023.10317366}, doi = {10.1109/APSIPAASC58517.2023.10317366}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/MabenGCCS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/YuenLS23, author = {Kwok Chin Yuen and Haoyang Li and Chng Eng Siong}, title = {{ASR} Model Adaptation for Rare Words Using Synthetic Data Generated by Multiple Text-To-Speech Systems}, booktitle = {Asia Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2023, Taipei, Taiwan, October 31 - Nov. 3, 2023}, pages = {1771--1778}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/APSIPAASC58517.2023.10317116}, doi = {10.1109/APSIPAASC58517.2023.10317116}, timestamp = {Sat, 02 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/YuenLS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/YipNMS23, author = {Jia Qi Yip and Dianwen Ng and Bin Ma and Chng Eng Siong}, title = {Analysis of Speech Separation Performance Degradation on Emotional Speech Mixtures}, booktitle = {Asia Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2023, Taipei, Taiwan, October 31 - Nov. 3, 2023}, pages = {2002--2007}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/APSIPAASC58517.2023.10317465}, doi = {10.1109/APSIPAASC58517.2023.10317465}, timestamp = {Sat, 02 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/YipNMS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/emnlp/SuranaHTC23, author = {Tanmay Surana and Thi{-}Nga Ho and Kyaw Zin Tun and Eng Siong Chng}, editor = {Houda Bouamor and Juan Pino and Kalika Bali}, title = {{CASSI:} Contextual and Semantic Structure-based Interpolation Augmentation for Low-Resource {NER}}, booktitle = {Findings of the Association for Computational Linguistics: {EMNLP} 2023, Singapore, December 6-10, 2023}, pages = {9729--9742}, publisher = {Association for Computational Linguistics}, year = {2023}, url = {https://doi.org/10.18653/v1/2023.findings-emnlp.651}, doi = {10.18653/V1/2023.FINDINGS-EMNLP.651}, timestamp = {Fri, 12 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/emnlp/SuranaHTC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/GuptaPHTKTCG23, author = {Kshitij Gupta and Chaiyasait Prachaseree and Thi{-}Nga Ho and Kyaw Zin Tun and Jia Xin Koh and Ying Ying Tan and Eng Siong Chng and Chalapathi GSS}, editor = {Lei Wang and Yanfeng Lu and Minghui Dong}, title = {Singaporean Conversational English-Malay Code-Switching Speech: An Analysis Based on Code-switching Points and Part -of-Speech}, booktitle = {International Conference on Asian Language Processing, {IALP} 2023, Singapore, November 18-20, 2023}, pages = {95--99}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/IALP61005.2023.10337279}, doi = {10.1109/IALP61005.2023.10337279}, timestamp = {Wed, 17 Jan 2024 17:11:26 +0100}, biburl = {https://dblp.org/rec/conf/ialp/GuptaPHTKTCG23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenHWC23, author = {Chen Chen and Yuchen Hu and Weiwei Weng and Eng Siong Chng}, title = {Metric-Oriented Speech Enhancement Using Diffusion Probabilistic Model}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10095046}, doi = {10.1109/ICASSP49357.2023.10095046}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenHWC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenHZSC23, author = {Chen Chen and Yuchen Hu and Heqing Zou and Linhui Sun and Eng Siong Chng}, title = {Unsupervised Noise Adaptation Using Data Simulation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10095441}, doi = {10.1109/ICASSP49357.2023.10095441}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenHZSC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuCLZC23, author = {Yuchen Hu and Chen Chen and Ruizhe Li and Qiushi Zhu and Eng Siong Chng}, title = {Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096615}, doi = {10.1109/ICASSP49357.2023.10096615}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HuCLZC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuCZZC23, author = {Yuchen Hu and Chen Chen and Heqing Zou and Xionghu Zhong and Eng Siong Chng}, title = {Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096050}, doi = {10.1109/ICASSP49357.2023.10096050}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HuCZZC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NgZYYNZMNCM23, author = {Dianwen Ng and Ruixi Zhang and Jia Qi Yip and Zhao Yang and Jinjie Ni and Chong Zhang and Yukun Ma and Chongjia Ni and Eng Siong Chng and Bin Ma}, title = {De'hubert: Disentangling Noise in a Self-Supervised Model for Robust Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096603}, doi = {10.1109/ICASSP49357.2023.10096603}, timestamp = {Fri, 10 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/NgZYYNZMNCM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NgZYZMNNCM23, author = {Dianwen Ng and Ruixi Zhang and Jia Qi Yip and Chong Zhang and Yukun Ma and Trung Hieu Nguyen and Chongjia Ni and Eng Siong Chng and Bin Ma}, title = {Contrastive Speech Mixup for Low-Resource Keyword Spotting}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096976}, doi = {10.1109/ICASSP49357.2023.10096976}, timestamp = {Fri, 10 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/NgZYZMNNCM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/RajaaADGC23, author = {Shangeth Rajaa and Kriti Anandan and Swaraj Dalmia and Tarun Gupta and Eng Siong Chng}, title = {Improving Spoken Language Identification with Map-Mix}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10095765}, doi = {10.1109/ICASSP49357.2023.10095765}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/RajaaADGC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SholokhovKLC23, author = {Alexey Sholokhov and Nikita Kuzmin and Kong Aik Lee and Eng Siong Chng}, title = {Probabilistic Back-ends for Online Speaker Recognition and Clustering}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10097032}, doi = {10.1109/ICASSP49357.2023.10097032}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/SholokhovKLC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/YangXHCL23, author = {Yuhang Yang and Haihua Xu and Hao Huang and Eng Siong Chng and Sheng Li}, title = {Speech-Text Based Multi-Modal Training with Bidirectional Attention for Improved Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing {ICASSP} 2023, Rhodes Island, Greece, June 4-10, 2023}, pages = {1--5}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICASSP49357.2023.10096726}, doi = {10.1109/ICASSP49357.2023.10096726}, timestamp = {Fri, 10 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/YangXHCL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/HuLCZZC23, author = {Yuchen Hu and Ruizhe Li and Chen Chen and Heqing Zou and Qiushi Zhu and Eng Siong Chng}, title = {Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition}, booktitle = {Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, {IJCAI} 2023, 19th-25th August 2023, Macao, SAR, China}, pages = {5076--5084}, publisher = {ijcai.org}, year = {2023}, url = {https://doi.org/10.24963/ijcai.2023/564}, doi = {10.24963/IJCAI.2023/564}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/HuLCZZC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/GuoQHS23, author = {Yachao Guo and Zhibin Qiu and Hao Huang and Chng Eng Siong}, title = {Improved Keyword Recognition Based on Aho-Corasick Automaton}, booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2023, Gold Coast, Australia, June 18-23, 2023}, pages = {1--7}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/IJCNN54540.2023.10191315}, doi = {10.1109/IJCNN54540.2023.10191315}, timestamp = {Wed, 09 Aug 2023 16:25:09 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/GuoQHS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/SiZLWWDCL23, author = {Yuke Si and Yan Zhang and Yuhang Li and Xiaobao Wang and Longbiao Wang and Jianwu Dang and Eng Siong Chng and Haizhou Li}, title = {Local and Global Context Modeling with Relation Matching Task for Dialog Act Recognition}, booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2023, Gold Coast, Australia, June 18-23, 2023}, pages = {1--8}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/IJCNN54540.2023.10191831}, doi = {10.1109/IJCNN54540.2023.10191831}, timestamp = {Tue, 21 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ijcnn/SiZLWWDCL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/0075HYSCS23, author = {Chen Chen and Yuchen Hu and Chao{-}Han Huck Yang and Sabato Marco Siniscalchi and Pin{-}Yu Chen and Chng Eng Siong}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, title = {HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models}, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, year = {2023}, url = {http://papers.nips.cc/paper\_files/paper/2023/hash/6492267465a7ac507be1f9fd1174e78d-Abstract-Datasets\_and\_Benchmarks.html}, timestamp = {Fri, 01 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/0075HYSCS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ssp/KhandelwalDKC23, author = {Tanmay Khandelwal and Rohan Kumar Das and Andrew Koh and Eng Siong Chng}, title = {Leveraging Audio-Tagging Assisted Sound Event Detection using Weakified Strong Labels and Frequency Dynamic Convolutions}, booktitle = {{IEEE} Statistical Signal Processing Workshop, {SSP} 2023, Hanoi, Vietnam, July 2-5, 2023}, pages = {329--333}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/SSP53291.2023.10208013}, doi = {10.1109/SSP53291.2023.10208013}, timestamp = {Thu, 17 Aug 2023 15:16:12 +0200}, biburl = {https://dblp.org/rec/conf/ssp/KhandelwalDKC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-08229, author = {Shangeth Rajaa and Kriti Anandan and Swaraj Dalmia and Tarun Gupta and Eng Siong Chng}, title = {Improving Spoken Language Identification with Map-Mix}, journal = {CoRR}, volume = {abs/2302.08229}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.08229}, doi = {10.48550/ARXIV.2302.08229}, eprinttype = {arXiv}, eprint = {2302.08229}, timestamp = {Mon, 20 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-08229.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-09523, author = {Alexey Sholokhov and Nikita Kuzmin and Kong Aik Lee and Eng Siong Chng}, title = {Probabilistic Back-ends for Online Speaker Recognition and Clustering}, journal = {CoRR}, volume = {abs/2302.09523}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.09523}, doi = {10.48550/ARXIV.2302.09523}, eprinttype = {arXiv}, eprint = {2302.09523}, timestamp = {Thu, 23 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-09523.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-11131, author = {Yuchen Hu and Chen Chen and Heqing Zou and Xionghu Zhong and Eng Siong Chng}, title = {Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End Noise-Robust Speech Separation}, journal = {CoRR}, volume = {abs/2302.11131}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.11131}, doi = {10.48550/ARXIV.2302.11131}, eprinttype = {arXiv}, eprint = {2302.11131}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-11131.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-11362, author = {Yuchen Hu and Chen Chen and Ruizhe Li and Qiushi Zhu and Eng Siong Chng}, title = {Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition}, journal = {CoRR}, volume = {abs/2302.11362}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.11362}, doi = {10.48550/ARXIV.2302.11362}, eprinttype = {arXiv}, eprint = {2302.11362}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-11362.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-11981, author = {Chen Chen and Yuchen Hu and Heqing Zou and Linhui Sun and Eng Siong Chng}, title = {Unsupervised Noise adaptation using Data Simulation}, journal = {CoRR}, volume = {abs/2302.11981}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.11981}, doi = {10.48550/ARXIV.2302.11981}, eprinttype = {arXiv}, eprint = {2302.11981}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-11981.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-11989, author = {Chen Chen and Yuchen Hu and Weiwei Weng and Eng Siong Chng}, title = {Metric-oriented Speech Enhancement using Diffusion Probabilistic Model}, journal = {CoRR}, volume = {abs/2302.11989}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.11989}, doi = {10.48550/ARXIV.2302.11989}, eprinttype = {arXiv}, eprint = {2302.11989}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-11989.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-14597, author = {Dianwen Ng and Ruixi Zhang and Jia Qi Yip and Zhao Yang and Jinjie Ni and Chong Zhang and Yukun Ma and Chongjia Ni and Eng Siong Chng and Bin Ma}, title = {deHuBERT: Disentangling Noise in a Self-supervised Model for Robust Speech Recognition}, journal = {CoRR}, volume = {abs/2302.14597}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.14597}, doi = {10.48550/ARXIV.2302.14597}, eprinttype = {arXiv}, eprint = {2302.14597}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-14597.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2304-04974, author = {Yuchen Hu and Chen Chen and Qiushi Zhu and Eng Siong Chng}, title = {Wav2code: Restore Clean Speech Representations via Codebook Lookup for Noise-Robust {ASR}}, journal = {CoRR}, volume = {abs/2304.04974}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2304.04974}, doi = {10.48550/ARXIV.2304.04974}, eprinttype = {arXiv}, eprint = {2304.04974}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2304-04974.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-01170, author = {Dianwen Ng and Ruixi Zhang and Jia Qi Yip and Chong Zhang and Yukun Ma and Trung Hieu Nguyen and Chongjia Ni and Eng Siong Chng and Bin Ma}, title = {Contrastive Speech Mixup for Low-resource Keyword Spotting}, journal = {CoRR}, volume = {abs/2305.01170}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.01170}, doi = {10.48550/ARXIV.2305.01170}, eprinttype = {arXiv}, eprint = {2305.01170}, timestamp = {Fri, 05 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-01170.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-09212, author = {Yuchen Hu and Ruizhe Li and Chen Chen and Heqing Zou and Qiushi Zhu and Eng Siong Chng}, title = {Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition}, journal = {CoRR}, volume = {abs/2305.09212}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.09212}, doi = {10.48550/ARXIV.2305.09212}, eprinttype = {arXiv}, eprint = {2305.09212}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-09212.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-09299, author = {Heqing Zou and Meng Shen and Chen Chen and Yuchen Hu and Deepu Rajan and Eng Siong Chng}, title = {UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning}, journal = {CoRR}, volume = {abs/2305.09299}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.09299}, doi = {10.48550/ARXIV.2305.09299}, eprinttype = {arXiv}, eprint = {2305.09299}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-09299.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-10761, author = {Zizheng Zhang and Chen Chen and Xiang Liu and Yuchen Hu and Eng Siong Chng}, title = {Noise-aware Speech Separation with Contrastive Learning}, journal = {CoRR}, volume = {abs/2305.10761}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.10761}, doi = {10.48550/ARXIV.2305.10761}, eprinttype = {arXiv}, eprint = {2305.10761}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-10761.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-12121, author = {Jia Qi Yip and Tuan Truong and Dianwen Ng and Chong Zhang and Yukun Ma and Trung Hieu Nguyen and Chongjia Ni and Shengkui Zhao and Eng Siong Chng and Bin Ma}, title = {ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention}, journal = {CoRR}, volume = {abs/2305.12121}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.12121}, doi = {10.48550/ARXIV.2305.12121}, eprinttype = {arXiv}, eprint = {2305.12121}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-12121.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-12460, author = {Leander Melroy Maben and Zixun Guo and Chen Chen and Utkarsh Chudiwal and Chng Eng Siong}, title = {Study of GANs for Noisy Speech Simulation from Clean Speech}, journal = {CoRR}, volume = {abs/2305.12460}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.12460}, doi = {10.48550/ARXIV.2305.12460}, eprinttype = {arXiv}, eprint = {2305.12460}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-12460.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-16932, author = {Chen Chen and Chao{-}Han Huck Yang and Kai Li and Yuchen Hu and Pin{-}Jui Ku and Eng Siong Chng}, title = {A Neural State-Space Model Approach to Efficient Speech Separation}, journal = {CoRR}, volume = {abs/2305.16932}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.16932}, doi = {10.48550/ARXIV.2305.16932}, eprinttype = {arXiv}, eprint = {2305.16932}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-16932.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-10563, author = {Yuchen Hu and Ruizhe Li and Chen Chen and Chengwei Qin and Qiushi Zhu and Eng Siong Chng}, title = {Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition}, journal = {CoRR}, volume = {abs/2306.10563}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.10563}, doi = {10.48550/ARXIV.2306.10563}, eprinttype = {arXiv}, eprint = {2306.10563}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-10563.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-10567, author = {Yuchen Hu and Chen Chen and Ruizhe Li and Heqing Zou and Eng Siong Chng}, title = {{MIR-GAN:} Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition}, journal = {CoRR}, volume = {abs/2306.10567}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.10567}, doi = {10.48550/ARXIV.2306.10567}, eprinttype = {arXiv}, eprint = {2306.10567}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-10567.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2307-08029, author = {Yuchen Hu and Chen Chen and Ruizhe Li and Qiushi Zhu and Eng Siong Chng}, title = {Noise-aware Speech Enhancement using Diffusion Probabilistic Model}, journal = {CoRR}, volume = {abs/2307.08029}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2307.08029}, doi = {10.48550/ARXIV.2307.08029}, eprinttype = {arXiv}, eprint = {2307.08029}, timestamp = {Fri, 03 May 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2307-08029.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-07458, author = {Jia Qi Yip and Dianwen Ng and Bin Ma and Chng Eng Siong}, title = {Analysis of Speech Separation Performance Degradation on Emotional Speech Mixtures}, journal = {CoRR}, volume = {abs/2309.07458}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.07458}, doi = {10.48550/ARXIV.2309.07458}, eprinttype = {arXiv}, eprint = {2309.07458}, timestamp = {Tue, 19 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-07458.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-07466, author = {Ansh Mishra and Jia Qi Yip and Eng Siong Chng}, title = {Codec Data Augmentation for Time-domain Heart Sound Classification}, journal = {CoRR}, volume = {abs/2309.07466}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.07466}, doi = {10.48550/ARXIV.2309.07466}, eprinttype = {arXiv}, eprint = {2309.07466}, timestamp = {Wed, 20 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-07466.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-09413, author = {Dianwen Ng and Chong Zhang and Ruixi Zhang and Yukun Ma and Fabian Ritter Gutierrez and Trung Hieu Nguyen and Chongjia Ni and Shengkui Zhao and Eng Siong Chng and Bin Ma}, title = {Are Soft Prompts Good Zero-shot Learners for Speech Recognition?}, journal = {CoRR}, volume = {abs/2309.09413}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.09413}, doi = {10.48550/ARXIV.2309.09413}, eprinttype = {arXiv}, eprint = {2309.09413}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-09413.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-12608, author = {Jia Qi Yip and Shengkui Zhao and Yukun Ma and Chongjia Ni and Chong Zhang and Hao Wang and Trung Hieu Nguyen and Kun Zhou and Dianwen Ng and Eng Siong Chng and Bin Ma}, title = {{SPGM:} Prioritizing Local Features for enhanced speech separation performance}, journal = {CoRR}, volume = {abs/2309.12608}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.12608}, doi = {10.48550/ARXIV.2309.12608}, eprinttype = {arXiv}, eprint = {2309.12608}, timestamp = {Mon, 16 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-12608.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-14838, author = {Duc{-}Tuan Truong and Ruijie Tao and Jia Qi Yip and Kong Aik Lee and Eng Siong Chng}, title = {Emphasized Non-Target Speaker Knowledge in Knowledge Distillation for Automatic Speaker Verification}, journal = {CoRR}, volume = {abs/2309.14838}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.14838}, doi = {10.48550/ARXIV.2309.14838}, eprinttype = {arXiv}, eprint = {2309.14838}, timestamp = {Mon, 16 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-14838.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-15701, author = {Chen Chen and Yuchen Hu and Chao{-}Han Huck Yang and Sabato Marco Siniscalchi and Pin{-}Yu Chen and Eng Siong Chng}, title = {HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models}, journal = {CoRR}, volume = {abs/2309.15701}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.15701}, doi = {10.48550/ARXIV.2309.15701}, eprinttype = {arXiv}, eprint = {2309.15701}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-15701.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2310-13013, author = {Chen Chen and Yuchen Hu and Chao{-}Han Huck Yang and Hexin Liu and Sabato Marco Siniscalchi and Eng Siong Chng}, title = {Generative error correction for code-switching speech recognition using large language models}, journal = {CoRR}, volume = {abs/2310.13013}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2310.13013}, doi = {10.48550/ARXIV.2310.13013}, eprinttype = {arXiv}, eprint = {2310.13013}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2310-13013.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-12153, author = {Fabian Ritter Gutierrez and Kuan{-}Po Huang and Dianwen Ng and Jeremy Heng Meng Wong and Hung{-}yi Lee and Eng Siong Chng and Nancy F. Chen}, title = {Noise robust distillation of self-supervised speech models via correlation metrics}, journal = {CoRR}, volume = {abs/2312.12153}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.12153}, doi = {10.48550/ARXIV.2312.12153}, eprinttype = {arXiv}, eprint = {2312.12153}, timestamp = {Wed, 17 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-12153.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jstsp/LiuGKCSK22, author = {Hexin Liu and Leibny Paola Garc{\'{\i}}a{-}Perera and Andy W. H. Khong and Eng Siong Chng and Suzy J. Styles and Sanjeev Khudanpur}, title = {Efficient Self-Supervised Learning Representations for Spoken Language Identification}, journal = {{IEEE} J. Sel. Top. Signal Process.}, volume = {16}, number = {6}, pages = {1296--1307}, year = {2022}, url = {https://doi.org/10.1109/JSTSP.2022.3201445}, doi = {10.1109/JSTSP.2022.3201445}, timestamp = {Sun, 13 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jstsp/LiuGKCSK22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/speech/GuoWDCN22, author = {Lili Guo and Longbiao Wang and Jianwu Dang and Eng Siong Chng and Seiichi Nakagawa}, title = {Learning affective representations based on magnitude and dynamic relative phase information for speech emotion recognition}, journal = {Speech Commun.}, volume = {136}, pages = {118--127}, year = {2022}, url = {https://doi.org/10.1016/j.specom.2021.11.005}, doi = {10.1016/J.SPECOM.2021.11.005}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/speech/GuoWDCN22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dcase/XiaoLKSCPW22, author = {Yang Xiao and Xubo Liu and James A. King and Arshdeep Singh and Eng Siong Chng and Mark D. Plumbley and Wenwu Wang}, editor = {Mathieu Lagrange and Annamaria Mesaros and Thomas Pellegrini and Ga{\"{e}}l Richard and Romain Serizel and Dan Stowell}, title = {Continual Learning for On-Ddevice Environmental Sound Classification}, booktitle = {Proceedings of the 7th Workshop on Detection and Classification of Acoustic Scenes and Events 2022, {DCASE} 2022, Nancy, France, November 3-4, 2022}, publisher = {Tampere University}, year = {2022}, url = {https://dcase.community/documents/workshop2022/proceedings/DCASE2022Workshop\_Xiao\_47.pdf}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/dcase/XiaoLKSCPW22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NgCTFC22, author = {Dianwen Ng and Yunqi Chen and Biao Tian and Qiang Fu and Eng Siong Chng}, title = {Convmixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-Field Keyword Spotting}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {3603--3607}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747025}, doi = {10.1109/ICASSP43922.2022.9747025}, timestamp = {Tue, 07 Jun 2022 17:34:47 +0200}, biburl = {https://dblp.org/rec/conf/icassp/NgCTFC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenHHQZC22, author = {Chen Chen and Yuchen Hu and Nana Hou and Xiaofeng Qi and Heqing Zou and Eng Siong Chng}, title = {Self-Critical Sequence Training for Automatic Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {3688--3692}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746668}, doi = {10.1109/ICASSP43922.2022.9746668}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenHHQZC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenHHSC22, author = {Chen Chen and Nana Hou and Yuchen Hu and Shashank Shirol and Eng Siong Chng}, title = {Noise-Robust Speech Recognition With 10 Minutes Unparalleled In-Domain Data}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {4298--4302}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747755}, doi = {10.1109/ICASSP43922.2022.9747755}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenHHSC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuHCC22, author = {Yuchen Hu and Nana Hou and Chen Chen and Eng Siong Chng}, title = {Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6292--6296}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746314}, doi = {10.1109/ICASSP43922.2022.9746314}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HuHCC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XueSZNC22, author = {Fuzhao Xue and Aixin Sun and Hao Zhang and Jinjie Ni and Eng Siong Chng}, title = {An Embarrassingly Simple Model for Dialogue Relation Extraction}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6707--6711}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747486}, doi = {10.1109/ICASSP43922.2022.9747486}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XueSZNC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/GeXWCDL22, author = {Meng Ge and Chenglin Xu and Longbiao Wang and Eng Siong Chng and Jianwu Dang and Haizhou Li}, title = {L-SpEx: Localized Target Speaker Extraction}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7287--7291}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746221}, doi = {10.1109/ICASSP43922.2022.9746221}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/GeXWCDL22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ZouSCRC22, author = {Heqing Zou and Yuke Si and Chen Chen and Deepu Rajan and Eng Siong Chng}, title = {Speech Emotion Recognition with Co-Attention Based Multi-Level Acoustic Information}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7367--7371}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747095}, doi = {10.1109/ICASSP43922.2022.9747095}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ZouSCRC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KohXS22, author = {Andrew Koh and Fuzhao Xue and Chng Eng Siong}, title = {Automated Audio Captioning Using Transfer Learning and Reconstruction Latent Space Similarity Regularization}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7722--7726}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747676}, doi = {10.1109/ICASSP43922.2022.9747676}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/KohXS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/PengZXHC22, author = {Yizhou Peng and Jicheng Zhang and Haihua Xu and Hao Huang and Eng Siong Chng}, title = {Minimum Word Error Training For Non-Autoregressive Transformer-Based Code-Switching {ASR}}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7807--7811}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746830}, doi = {10.1109/ICASSP43922.2022.9746830}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/PengZXHC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GuptaTAC22, author = {Tarun Gupta and Duc{-}Tuan Truong and Tran The Anh and Eng Siong Chng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {1978--1982}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-567}, doi = {10.21437/INTERSPEECH.2022-567}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/GuptaTAC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChenHHZQC22, author = {Chen Chen and Nana Hou and Yuchen Hu and Heqing Zou and Xiaofeng Qi and Eng Siong Chng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Interactive Auido-text Representation for Automated Audio Captioning with Contrastive Learning}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2773--2777}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10510}, doi = {10.21437/INTERSPEECH.2022-10510}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ChenHHZQC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XiaoHC22, author = {Yang Xiao and Nana Hou and Eng Siong Chng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {3764--3768}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10500}, doi = {10.21437/INTERSPEECH.2022-10500}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XiaoHC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GuoCC22, author = {Zixun Guo and Chen Chen and Eng Siong Chng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {{DENT-DDSP:} Data-efficient noisy speech generator using differentiable digital signal processors for explicit distortion modelling and noise-robust speech recognition}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {3799--3803}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-763}, doi = {10.21437/INTERSPEECH.2022-763}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/GuoCC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/ZhangYHXWCBZCX22, author = {Ao Zhang and Fan Yu and Kaixun Huang and Lei Xie and Longbiao Wang and Eng Siong Chng and Hui Bu and Binbin Zhang and Wei Chen and Xin Xu}, editor = {Kong Aik Lee and Hung{-}yi Lee and Yanfeng Lu and Minghui Dong}, title = {The {ISCSLP} 2022 Intelligent Cockpit Speech Recognition Challenge {(ICSRC):} Dataset, Tracks, Baseline and Results}, booktitle = {13th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2022, Singapore, December 11-14, 2022}, pages = {507--511}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ISCSLP57327.2022.10037868}, doi = {10.1109/ISCSLP57327.2022.10037868}, timestamp = {Fri, 17 Feb 2023 18:27:20 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/ZhangYHXWCBZCX22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-05863, author = {Dianwen Ng and Yunqi Chen and Biao Tian and Qiang Fu and Eng Siong Chng}, title = {ConvMixer: Feature Interactive Convolution with Curriculum Learning for Small Footprint and Noisy Far-field Keyword Spotting}, journal = {CoRR}, volume = {abs/2201.05863}, year = {2022}, url = {https://arxiv.org/abs/2201.05863}, eprinttype = {arXiv}, eprint = {2201.05863}, timestamp = {Thu, 20 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-05863.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-09995, author = {Meng Ge and Chenglin Xu and Longbiao Wang and Eng Siong Chng and Jianwu Dang and Haizhou Li}, title = {L-SpEx: Localized Target Speaker Extraction}, journal = {CoRR}, volume = {abs/2202.09995}, year = {2022}, url = {https://arxiv.org/abs/2202.09995}, eprinttype = {arXiv}, eprint = {2202.09995}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-09995.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-11774, author = {Tarun Gupta and Duc{-}Tuan Truong and Tran The Anh and Chng Eng Siong}, title = {Estimation of speaker age and height from speech signal using bi-encoder transformer mixture model}, journal = {CoRR}, volume = {abs/2203.11774}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.11774}, doi = {10.48550/ARXIV.2203.11774}, eprinttype = {arXiv}, eprint = {2203.11774}, timestamp = {Tue, 29 Mar 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-11774.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-14838, author = {Yuchen Hu and Nana Hou and Chen Chen and Eng Siong Chng}, title = {Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition}, journal = {CoRR}, volume = {abs/2203.14838}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.14838}, doi = {10.48550/ARXIV.2203.14838}, eprinttype = {arXiv}, eprint = {2203.14838}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-14838.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-15321, author = {Chen Chen and Nana Hou and Yuchen Hu and Shashank Shirol and Eng Siong Chng}, title = {Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data}, journal = {CoRR}, volume = {abs/2203.15321}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.15321}, doi = {10.48550/ARXIV.2203.15321}, eprinttype = {arXiv}, eprint = {2203.15321}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-15321.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-15326, author = {Heqing Zou and Yuke Si and Chen Chen and Deepu Rajan and Eng Siong Chng}, title = {Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information}, journal = {CoRR}, volume = {abs/2203.15326}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.15326}, doi = {10.48550/ARXIV.2203.15326}, eprinttype = {arXiv}, eprint = {2203.15326}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-15326.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-15526, author = {Chen Chen and Nana Hou and Yuchen Hu and Heqing Zou and Xiaofeng Qi and Eng Siong Chng}, title = {Interactive Audio-text Representation for Automated Audio Captioning with Contrastive Learning}, journal = {CoRR}, volume = {abs/2203.15526}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.15526}, doi = {10.48550/ARXIV.2203.15526}, eprinttype = {arXiv}, eprint = {2203.15526}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-15526.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-16361, author = {Yang Xiao and Nana Hou and Eng Siong Chng}, title = {Rainbow Keywords: Efficient Incremental Learning for Online Spoken Keyword Spotting}, journal = {CoRR}, volume = {abs/2203.16361}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.16361}, doi = {10.48550/ARXIV.2203.16361}, eprinttype = {arXiv}, eprint = {2203.16361}, timestamp = {Mon, 04 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-16361.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-05445, author = {Dianwen Ng and Jin Hui Pang and Yang Xiao and Biao Tian and Qiang Fu and Eng Siong Chng}, title = {Small Footprint Multi-channel ConvMixer for Keyword Spotting with Centroid Based Awareness}, journal = {CoRR}, volume = {abs/2204.05445}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.05445}, doi = {10.48550/ARXIV.2204.05445}, eprinttype = {arXiv}, eprint = {2204.05445}, timestamp = {Tue, 19 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-05445.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-06260, author = {Chen Chen and Yuchen Hu and Nana Hou and Xiaofeng Qi and Heqing Zou and Eng Siong Chng}, title = {Self-critical Sequence Training for Automatic Speech Recognition}, journal = {CoRR}, volume = {abs/2204.06260}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.06260}, doi = {10.48550/ARXIV.2204.06260}, eprinttype = {arXiv}, eprint = {2204.06260}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-06260.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-01918, author = {Andrew Koh and Soham Tiwari and Chng Eng Siong}, title = {Automated Audio Captioning with Epochal Difficult Captions for Curriculum Learning}, journal = {CoRR}, volume = {abs/2206.01918}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.01918}, doi = {10.48550/ARXIV.2206.01918}, eprinttype = {arXiv}, eprint = {2206.01918}, timestamp = {Mon, 13 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-01918.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-14659, author = {Andrew Koh and Eng Siong Chng}, title = {Language-Based Audio Retrieval with Converging Tied Layers and Contrastive Loss}, journal = {CoRR}, volume = {abs/2206.14659}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.14659}, doi = {10.48550/ARXIV.2206.14659}, eprinttype = {arXiv}, eprint = {2206.14659}, timestamp = {Mon, 04 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-14659.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2207-04176, author = {Yizhou Peng and Yufei Liu and Jicheng Zhang and Haihua Xu and Yi He and Hao Huang and Eng Siong Chng}, title = {Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition}, journal = {CoRR}, volume = {abs/2207.04176}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2207.04176}, doi = {10.48550/ARXIV.2207.04176}, eprinttype = {arXiv}, eprint = {2207.04176}, timestamp = {Thu, 14 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2207-04176.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2207-04177, author = {Jicheng Zhang and Yizhou Peng and Haihua Xu and Yi He and Eng Siong Chng and Hao Huang}, title = {Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder}, journal = {CoRR}, volume = {abs/2207.04177}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2207.04177}, doi = {10.48550/ARXIV.2207.04177}, eprinttype = {arXiv}, eprint = {2207.04177}, timestamp = {Thu, 14 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2207-04177.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2207-07429, author = {Yang Xiao and Xubo Liu and James A. King and Arshdeep Singh and Eng Siong Chng and Mark D. Plumbley and Wenwu Wang}, title = {Continual Learning For On-Device Environmental Sound Classification}, journal = {CoRR}, volume = {abs/2207.07429}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2207.07429}, doi = {10.48550/ARXIV.2207.07429}, eprinttype = {arXiv}, eprint = {2207.07429}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2207-07429.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2208-00987, author = {Zixun Guo and Chen Chen and Eng Siong Chng}, title = {{DENT-DDSP:} Data-efficient noisy speech generator using differentiable digital signal processors for explicit distortion modelling and noise-robust speech recognition}, journal = {CoRR}, volume = {abs/2208.00987}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2208.00987}, doi = {10.48550/ARXIV.2208.00987}, eprinttype = {arXiv}, eprint = {2208.00987}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2208-00987.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2209-06360, author = {Dianwen Ng and Jia Qi Yip and Tanmay Surana and Zhao Yang and Chong Zhang and Yukun Ma and Chongjia Ni and Eng Siong Chng and Bin Ma}, title = {{I2CR:} Improving Noise Robustness on Keyword Spotting Using Inter-Intra Contrastive Regularization}, journal = {CoRR}, volume = {abs/2209.06360}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2209.06360}, doi = {10.48550/ARXIV.2209.06360}, eprinttype = {arXiv}, eprint = {2209.06360}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2209-06360.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-00325, author = {Yuhang Yang and Haihua Xu and Hao Huang and Eng Siong Chng and Sheng Li}, title = {Speech-text based multi-modal training with bidirectional attention for improved speech recognition}, journal = {CoRR}, volume = {abs/2211.00325}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.00325}, doi = {10.48550/ARXIV.2211.00325}, eprinttype = {arXiv}, eprint = {2211.00325}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-00325.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-01585, author = {Ao Zhang and Fan Yu and Kaixun Huang and Lei Xie and Longbiao Wang and Eng Siong Chng and Hui Bu and Binbin Zhang and Wei Chen and Xin Xu}, title = {The {ISCSLP} 2022 Intelligent Cockpit Speech Recognition Challenge {(ICSRC):} Dataset, Tracks, Baseline and Results}, journal = {CoRR}, volume = {abs/2211.01585}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.01585}, doi = {10.48550/ARXIV.2211.01585}, eprinttype = {arXiv}, eprint = {2211.01585}, timestamp = {Fri, 04 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-01585.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-05301, author = {Chen Chen and Yuchen Hu and Qiang Zhang and Heqing Zou and Beier Zhu and Eng Siong Chng}, title = {Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning}, journal = {CoRR}, volume = {abs/2212.05301}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.05301}, doi = {10.48550/ARXIV.2212.05301}, eprinttype = {arXiv}, eprint = {2212.05301}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-05301.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-05356, author = {Abhinav Rao and Thi{-}Nga Ho and Eng Siong Chng}, title = {Punctuation Restoration for Singaporean Spoken Languages: English, Malay, and Mandarin}, journal = {CoRR}, volume = {abs/2212.05356}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.05356}, doi = {10.48550/ARXIV.2212.05356}, eprinttype = {arXiv}, eprint = {2212.05356}, timestamp = {Mon, 02 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-05356.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/XueSZC21, author = {Fuzhao Xue and Aixin Sun and Hao Zhang and Eng Siong Chng}, title = {GDPNet: Refining Latent Multi-View Graph for Relation Extraction}, booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9, 2021}, pages = {14194--14202}, publisher = {{AAAI} Press}, year = {2021}, url = {https://doi.org/10.1609/aaai.v35i16.17670}, doi = {10.1609/AAAI.V35I16.17670}, timestamp = {Mon, 04 Sep 2023 12:29:24 +0200}, biburl = {https://dblp.org/rec/conf/aaai/XueSZC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/KaushikPAC21, author = {Manav Kaushik and Van Tung Pham and Tran The Anh and Eng Siong Chng}, title = {End-to-End Speaker Age and Height Estimation using Attention Mechanism and Triplet Loss}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December 14-17, 2021}, pages = {1--8}, publisher = {{IEEE}}, year = {2021}, url = {https://ieeexplore.ieee.org/document/9689583}, timestamp = {Wed, 09 Feb 2022 09:03:08 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/KaushikPAC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/MaHPXC21, author = {Duo Ma and Nana Hou and Van Tung Pham and Haihua Xu and Eng Siong Chng}, title = {Multitask-based joint learning approach to robust {ASR} for radio communication speech}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December 14-17, 2021}, pages = {497--502}, publisher = {{IEEE}}, year = {2021}, url = {https://ieeexplore.ieee.org/document/9689671}, timestamp = {Wed, 09 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/MaHPXC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/ChenHMC21, author = {Chen Chen and Nana Hou and Duo Ma and Eng Siong Chng}, title = {Time Domain Speech Enhancement With Attentive Multi-scale Approach}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December 14-17, 2021}, pages = {679--683}, publisher = {{IEEE}}, year = {2021}, url = {https://ieeexplore.ieee.org/document/9689572}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/ChenHMC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/MaoKPXHWC21, author = {Tingzhi Mao and Yerbolat Khassanov and Van Tung Pham and Haihua Xu and Hao Huang and Aishan Wumaier and Eng Siong Chng}, title = {Enriching Under-Represented Named Entities for Improved Speech Recognition}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December 14-17, 2021}, pages = {1021--1025}, publisher = {{IEEE}}, year = {2021}, url = {https://ieeexplore.ieee.org/document/9689549}, timestamp = {Wed, 09 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/MaoKPXHWC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/PengZZXHLC21, author = {Yizhou Peng and Jicheng Zhang and Haobo Zhang and Haihua Xu and Hao Huang and Sheng Li and Eng Siong Chng}, title = {Multilingual Approach to Joint Speech and Accent Recognition with {DNN-HMM} Framework}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December 14-17, 2021}, pages = {1043--1048}, publisher = {{IEEE}}, year = {2021}, url = {https://ieeexplore.ieee.org/document/9689498}, timestamp = {Wed, 09 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/PengZZXHLC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/emnlp/ZhaoNLJCM21, author = {Yingzhu Zhao and Chongjia Ni and Cheung{-}Chi Leung and Shafiq R. Joty and Eng Siong Chng and Bin Ma}, editor = {Marie{-}Francine Moens and Xuanjing Huang and Lucia Specia and Scott Wen{-}tau Yih}, title = {A Unified Speaker Adaptation Approach for {ASR}}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021}, pages = {9339--9349}, publisher = {Association for Computational Linguistics}, year = {2021}, url = {https://doi.org/10.18653/v1/2021.emnlp-main.737}, doi = {10.18653/V1/2021.EMNLP-MAIN.737}, timestamp = {Fri, 16 Feb 2024 08:27:36 +0100}, biburl = {https://dblp.org/rec/conf/emnlp/ZhaoNLJCM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HouXC021, author = {Nana Hou and Chenglin Xu and Eng Siong Chng and Haizhou Li}, title = {Learning Disentangled Feature Representations for Speech Enhancement Via Adversarial Training}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {666--670}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413512}, doi = {10.1109/ICASSP39728.2021.9413512}, timestamp = {Thu, 08 Jul 2021 17:12:48 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HouXC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/GeXWCD021, author = {Meng Ge and Chenglin Xu and Longbiao Wang and Eng Siong Chng and Jianwu Dang and Haizhou Li}, title = {Multi-Stage Speaker Extraction with Utterance and Frame-Level Reference Signals}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6109--6113}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413359}, doi = {10.1109/ICASSP39728.2021.9413359}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/GeXWCD021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/GuoWXDC021, author = {Lili Guo and Longbiao Wang and Chenglin Xu and Jianwu Dang and Eng Siong Chng and Haizhou Li}, title = {Representation Learning with Spectro-Temporal-Channel Attention for Speech Emotion Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6304--6308}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414006}, doi = {10.1109/ICASSP39728.2021.9414006}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/GuoWXDC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ZhaoNLJCM21, author = {Yingzhu Zhao and Chongjia Ni and Cheung{-}Chi Leung and Shafiq R. Joty and Eng Siong Chng and Bin Ma}, title = {Preventing Early Endpointing for Online Automatic Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6813--6817}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413613}, doi = {10.1109/ICASSP39728.2021.9413613}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ZhaoNLJCM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhangPPXHC21, author = {Jicheng Zhang and Yizhou Peng and Van Tung Pham and Haihua Xu and Hao Huang and Eng Siong Chng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {E2E-Based Multi-Task Learning Approach to Joint Speech and Accent Recognition}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {1519--1523}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-1495}, doi = {10.21437/INTERSPEECH.2021-1495}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZhangPPXHC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChenPCZ21, author = {Weiguang Chen and Van Tung Pham and Eng Siong Chng and Xionghu Zhong}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Overlapped Speech Detection Based on Spectral and Spatial Feature Fusion}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4189--4193}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-2138}, doi = {10.21437/INTERSPEECH.2021-2138}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChenPCZ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/MaoKPXHC21, author = {Tingzhi Mao and Yerbolat Khassanov and Van Tung Pham and Haihua Xu and Hao Huang and Eng Siong Chng}, title = {Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid {ASR} Systems}, booktitle = {12th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2021, Hong Kong, January 24-27, 2021}, pages = {1--5}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ISCSLP49672.2021.9362062}, doi = {10.1109/ISCSLP49672.2021.9362062}, timestamp = {Mon, 22 Mar 2021 16:16:13 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/MaoKPXHC21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/ZengPXKCNM21, author = {Zhiping Zeng and Van Tung Pham and Haihua Xu and Yerbolat Khassanov and Eng Siong Chng and Chongjia Ni and Bin Ma}, title = {Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End {ASR} in Transfer Learning}, booktitle = {12th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2021, Hong Kong, January 24-27, 2021}, pages = {1--5}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ISCSLP49672.2021.9362086}, doi = {10.1109/ISCSLP49672.2021.9362086}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/ZengPXKCNM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2101-05056, author = {Manav Kaushik and Van Tung Pham and Eng Siong Chng}, title = {End-to-End Speaker Height and age estimation using Attention Mechanism with {LSTM-RNN}}, journal = {CoRR}, volume = {abs/2101.05056}, year = {2021}, url = {https://arxiv.org/abs/2101.05056}, eprinttype = {arXiv}, eprint = {2101.05056}, timestamp = {Fri, 22 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2101-05056.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-10701, author = {Duo Ma and Nana Hou and Van Tung Pham and Haihua Xu and Eng Siong Chng}, title = {Multitask-Based Joint Learning Approach To Robust {ASR} For Radio Communication Speech}, journal = {CoRR}, volume = {abs/2107.10701}, year = {2021}, url = {https://arxiv.org/abs/2107.10701}, eprinttype = {arXiv}, eprint = {2107.10701}, timestamp = {Thu, 29 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-10701.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2108-04692, author = {Andrew Koh and Fuzhao Xue and Eng Siong Chng}, title = {Automated Audio Captioning using Transfer Learning and Reconstruction Latent Space Similarity Regularization}, journal = {CoRR}, volume = {abs/2108.04692}, year = {2021}, url = {https://arxiv.org/abs/2108.04692}, eprinttype = {arXiv}, eprint = {2108.04692}, timestamp = {Wed, 11 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2108-04692.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-05267, author = {Yuchen Hu and Nana Hou and Chen Chen and Eng Siong Chng}, title = {Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition}, journal = {CoRR}, volume = {abs/2110.05267}, year = {2021}, url = {https://arxiv.org/abs/2110.05267}, eprinttype = {arXiv}, eprint = {2110.05267}, timestamp = {Mon, 26 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-05267.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-08545, author = {Yingzhu Zhao and Chongjia Ni and Cheung{-}Chi Leung and Shafiq R. Joty and Eng Siong Chng and Bin Ma}, title = {A Unified Speaker Adaptation Approach for {ASR}}, journal = {CoRR}, volume = {abs/2110.08545}, year = {2021}, url = {https://arxiv.org/abs/2110.08545}, eprinttype = {arXiv}, eprint = {2110.08545}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-08545.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-13653, author = {Shangeth Rajaa and Van Tung Pham and Chng Eng Siong}, title = {Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling}, journal = {CoRR}, volume = {abs/2110.13653}, year = {2021}, url = {https://arxiv.org/abs/2110.13653}, eprinttype = {arXiv}, eprint = {2110.13653}, timestamp = {Fri, 29 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-13653.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XuRCL20, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, title = {SpEx: Multi-Scale Time Domain Speaker Extraction Network}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {28}, pages = {1370--1384}, year = {2020}, url = {https://doi.org/10.1109/TASLP.2020.2987429}, doi = {10.1109/TASLP.2020.2987429}, timestamp = {Thu, 27 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/XuRCL20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/emnlp/YapKC20, author = {Boon Peng Yap and Andrew Koh and Eng Siong Chng}, editor = {Trevor Cohn and Yulan He and Yang Liu}, title = {Adapting {BERT} for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences}, booktitle = {Findings of the Association for Computational Linguistics: {EMNLP} 2020, Online Event, 16-20 November 2020}, series = {Findings of {ACL}}, volume = {{EMNLP} 2020}, pages = {41--46}, publisher = {Association for Computational Linguistics}, year = {2020}, url = {https://doi.org/10.18653/v1/2020.findings-emnlp.4}, doi = {10.18653/V1/2020.FINDINGS-EMNLP.4}, timestamp = {Wed, 23 Mar 2022 10:11:55 +0100}, biburl = {https://dblp.org/rec/conf/emnlp/YapKC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HaoXHXC020, author = {Xiang Hao and Chenglin Xu and Nana Hou and Lei Xie and Eng Siong Chng and Haizhou Li}, title = {Time-Domain Neural Network Approach for Speech Bandwidth Extension}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {866--870}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9054551}, doi = {10.1109/ICASSP40776.2020.9054551}, timestamp = {Tue, 01 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HaoXHXC020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/PhamXKZCNM020, author = {Van Tung Pham and Haihua Xu and Yerbolat Khassanov and Zhiping Zeng and Eng Siong Chng and Chongjia Ni and Bin Ma and Haizhou Li}, title = {Independent Language Modeling Architecture for End-To-End {ASR}}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {7059--7063}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9054116}, doi = {10.1109/ICASSP40776.2020.9054116}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/PhamXKZCNM020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhaoNLJCM20, author = {Yingzhu Zhao and Chongjia Ni and Cheung{-}Chi Leung and Shafiq R. Joty and Eng Siong Chng and Bin Ma}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Speech Transformer with Speaker Aware Persistent Memory}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {1261--1265}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1281}, doi = {10.21437/INTERSPEECH.2020-1281}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ZhaoNLJCM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GeXWCD020, author = {Meng Ge and Chenglin Xu and Longbiao Wang and Eng Siong Chng and Jianwu Dang and Haizhou Li}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {SpEx+: {A} Complete Time Domain Speaker Extraction Network}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {1406--1410}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1397}, doi = {10.21437/INTERSPEECH.2020-1397}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/GeXWCD020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhangXPHC20, author = {Haobo Zhang and Haihua Xu and Van Tung Pham and Hao Huang and Eng Siong Chng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-Switching Speech Recognition}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {2392--2396}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1582}, doi = {10.21437/INTERSPEECH.2020-1582}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ZhangXPHC20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HouXPZC020, author = {Nana Hou and Chenglin Xu and Van Tung Pham and Joey Tianyi Zhou and Eng Siong Chng and Haizhou Li}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Speaker and Phoneme-Aware Speech Bandwidth Extension with Residual Dual-Path Network}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {4064--4068}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1994}, doi = {10.21437/INTERSPEECH.2020-1994}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/HouXPZC020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HouXZC020, author = {Nana Hou and Chenglin Xu and Joey Tianyi Zhou and Eng Siong Chng and Haizhou Li}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Multi-Task Learning for End-to-End Noise-Robust Bandwidth Extension}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {4069--4073}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2022}, doi = {10.21437/INTERSPEECH.2020-2022}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/HouXZC020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhaoNLJCM20a, author = {Yingzhu Zhao and Chongjia Ni and Cheung{-}Chi Leung and Shafiq R. Joty and Eng Siong Chng and Bin Ma}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Universal Speech Transformer}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {5021--5025}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1716}, doi = {10.21437/INTERSPEECH.2020-1716}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ZhaoNLJCM20a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhaoNLJCM20b, author = {Yingzhu Zhao and Chongjia Ni and Cheung{-}Chi Leung and Shafiq R. Joty and Eng Siong Chng and Bin Ma}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Cross Attention with Monotonic Alignment for Speech Transformer}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {5031--5035}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1198}, doi = {10.21437/INTERSPEECH.2020-1198}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ZhaoNLJCM20b.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2004-08326, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, title = {SpEx: Multi-Scale Time Domain Speaker Extraction Network}, journal = {CoRR}, volume = {abs/2004.08326}, year = {2020}, url = {https://arxiv.org/abs/2004.08326}, eprinttype = {arXiv}, eprint = {2004.08326}, timestamp = {Thu, 23 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2004-08326.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2004-14762, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, title = {Time-domain speaker extraction network}, journal = {CoRR}, volume = {abs/2004.14762}, year = {2020}, url = {https://arxiv.org/abs/2004.14762}, eprinttype = {arXiv}, eprint = {2004.14762}, timestamp = {Sun, 03 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2004-14762.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-04686, author = {Meng Ge and Chenglin Xu and Longbiao Wang and Eng Siong Chng and Jianwu Dang and Haizhou Li}, title = {SpEx+: {A} Complete Time Domain Speaker Extraction Network}, journal = {CoRR}, volume = {abs/2005.04686}, year = {2020}, url = {https://arxiv.org/abs/2005.04686}, eprinttype = {arXiv}, eprint = {2005.04686}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-04686.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-08742, author = {Tingzhi Mao and Yerbolat Khassanov and Van Tung Pham and Haihua Xu and Hao Huang and Eng Siong Chng}, title = {Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid {ASR} Systems}, journal = {CoRR}, volume = {abs/2005.08742}, year = {2020}, url = {https://arxiv.org/abs/2005.08742}, eprinttype = {arXiv}, eprint = {2005.08742}, timestamp = {Fri, 22 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-08742.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-10407, author = {Zhiping Zeng and Van Tung Pham and Haihua Xu and Yerbolat Khassanov and Eng Siong Chng and Chongjia Ni and Bin Ma}, title = {Leveraging Text Data Using Hybrid Transformer-LSTM Based End-to-End {ASR} in Transfer Learning}, journal = {CoRR}, volume = {abs/2005.10407}, year = {2020}, url = {https://arxiv.org/abs/2005.10407}, eprinttype = {arXiv}, eprint = {2005.10407}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-10407.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2009-11795, author = {Boon Peng Yap and Andrew Koh and Eng Siong Chng}, title = {Adapting {BERT} for Word Sense Disambiguation with Gloss Selection Objective and Example Sentences}, journal = {CoRR}, volume = {abs/2009.11795}, year = {2020}, url = {https://arxiv.org/abs/2009.11795}, eprinttype = {arXiv}, eprint = {2009.11795}, timestamp = {Wed, 11 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2009-11795.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-11483, author = {Yizhou Peng and Jicheng Zhang and Haobo Zhang and Haihua Xu and Hao Huang and Eng Siong Chng}, title = {A multilingual approach to joint Speech and Accent Recognition with {DNN-HMM} framework}, journal = {CoRR}, volume = {abs/2010.11483}, year = {2020}, url = {https://arxiv.org/abs/2010.11483}, eprinttype = {arXiv}, eprint = {2010.11483}, timestamp = {Tue, 27 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-11483.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-12143, author = {Tingzhi Mao and Yerbolat Khassanov and Van Tung Pham and Haihua Xu and Hao Huang and Aishan Wumaier and Eng Siong Chng}, title = {Enriching Under-Represented Named-Entities To Improve Speech Recognition Performance}, journal = {CoRR}, volume = {abs/2010.12143}, year = {2020}, url = {https://arxiv.org/abs/2010.12143}, eprinttype = {arXiv}, eprint = {2010.12143}, timestamp = {Tue, 27 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-12143.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-09624, author = {Meng Ge and Chenglin Xu and Longbiao Wang and Eng Siong Chng and Jianwu Dang and Haizhou Li}, title = {Multi-stage Speaker Extraction with Utterance and Frame-Level Reference Signals}, journal = {CoRR}, volume = {abs/2011.09624}, year = {2020}, url = {https://arxiv.org/abs/2011.09624}, eprinttype = {arXiv}, eprint = {2011.09624}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-09624.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-06780, author = {Fuzhao Xue and Aixin Sun and Hao Zhang and Eng Siong Chng}, title = {GDPNet: Refining Latent Multi-View Graph for Relation Extraction}, journal = {CoRR}, volume = {abs/2012.06780}, year = {2020}, url = {https://arxiv.org/abs/2012.06780}, eprinttype = {arXiv}, eprint = {2012.06780}, timestamp = {Wed, 28 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-06780.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-13873, author = {Fuzhao Xue and Aixin Sun and Hao Zhang and Eng Siong Chng}, title = {An Embarrassingly Simple Model for Dialogue Relation Extraction}, journal = {CoRR}, volume = {abs/2012.13873}, year = {2020}, url = {https://arxiv.org/abs/2012.13873}, eprinttype = {arXiv}, eprint = {2012.13873}, timestamp = {Wed, 28 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-13873.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/VuZXC19, author = {Thi{-}Ly Vu and Zhiping Zeng and Haihua Xu and Eng Siong Chng}, title = {Audio Codec Simulation based Data Augmentation for Telephony Speech Recognition}, booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November 18-21, 2019}, pages = {198--203}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023257}, doi = {10.1109/APSIPAASC47483.2019.9023257}, timestamp = {Fri, 13 Mar 2020 10:17:58 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/VuZXC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/MakhijaHC19, author = {Karan Makhija and Thi{-}Nga Ho and Eng Siong Chng}, title = {Transfer Learning for Punctuation Prediction}, booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November 18-21, 2019}, pages = {268--273}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023200}, doi = {10.1109/APSIPAASC47483.2019.9023200}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/MakhijaHC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/HouXC019, author = {Nana Hou and Chenglin Xu and Eng Siong Chng and Haizhou Li}, title = {Domain Adversarial Training for Speech Enhancement}, booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November 18-21, 2019}, pages = {667--672}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023218}, doi = {10.1109/APSIPAASC47483.2019.9023218}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/HouXC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/MaLXC19, author = {Duo Ma and Guanyu Li and Haihua Xu and Eng Siong Chng}, title = {Improving code-switching speech recognition with data augmentation and system combination}, booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November 18-21, 2019}, pages = {1308--1312}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023316}, doi = {10.1109/APSIPAASC47483.2019.9023316}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/MaLXC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/XuRCL19, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, title = {Time-Domain Speaker Extraction Network}, booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU} 2019, Singapore, December 14-18, 2019}, pages = {327--334}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ASRU46091.2019.9004016}, doi = {10.1109/ASRU46091.2019.9004016}, timestamp = {Mon, 24 Feb 2020 17:51:31 +0100}, biburl = {https://dblp.org/rec/conf/asru/XuRCL19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuRC019, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, title = {Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {6990--6994}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8683874}, doi = {10.1109/ICASSP.2019.8683874}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XuRC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmlsc/NguyenTCHVC19, author = {Trang M. Nguyen and Van{-}Lien Tran and Duy{-}Cat Can and Quang{-}Thuy Ha and Ly T. Vu and Engsiong Chng}, title = {{QASA:} Advanced Document Retriever for Open-Domain Question Answering by Learning to Rank Question-Aware Self-Attentive Document Representations}, booktitle = {Proceedings of the 3rd International Conference on Machine Learning and Soft Computing, {ICMLSC} 2019, Da Lat, Vietnam, January 25-28, 2019}, pages = {221--225}, publisher = {{ACM}}, year = {2019}, url = {https://doi.org/10.1145/3310986.3310999}, doi = {10.1145/3310986.3310999}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icmlsc/NguyenTCHVC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TianC019, author = {Xiaohai Tian and Eng Siong Chng and Haizhou Li}, editor = {Gernot Kubin and Zdravko Kacic}, title = {A Speaker-Dependent WaveNet for Voice Conversion with Non-Parallel Data}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {201--205}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1514}, doi = {10.21437/INTERSPEECH.2019-1514}, timestamp = {Fri, 29 Jan 2021 17:41:10 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/TianC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/RaoXC019, author = {Wei Rao and Chenglin Xu and Eng Siong Chng and Haizhou Li}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Target Speaker Extraction for Multi-Talker Speaker Verification}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {1273--1277}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1410}, doi = {10.21437/INTERSPEECH.2019-1410}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/RaoXC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/KhassanovXPZCNM19, author = {Yerbolat Khassanov and Haihua Xu and Van Tung Pham and Zhiping Zeng and Eng Siong Chng and Chongjia Ni and Bin Ma}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {2160--2164}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1867}, doi = {10.21437/INTERSPEECH.2019-1867}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/KhassanovXPZCNM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZengKPXC019, author = {Zhiping Zeng and Yerbolat Khassanov and Van Tung Pham and Haihua Xu and Eng Siong Chng and Haizhou Li}, editor = {Gernot Kubin and Zdravko Kacic}, title = {On the End-to-End Solution to Mandarin-English Code-Switching Speech Recognition}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {2165--2169}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1429}, doi = {10.21437/INTERSPEECH.2019-1429}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ZengKPXC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/KhassanovZPXC19, author = {Yerbolat Khassanov and Zhiping Zeng and Van Tung Pham and Haihua Xu and Eng Siong Chng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {3505--3509}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1858}, doi = {10.21437/INTERSPEECH.2019-1858}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/KhassanovZPXC19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iwsds/VuKSB19, author = {Thi{-}Ly Vu and Zin Tun Kyaw and Chng Eng Siong and Rafael E. Banchs}, editor = {Erik Marchi and Sabato Marco Siniscalchi and Sandro Cumani and Valerio Mario Salerno and Haizhou Li}, title = {Online {FAQ} Chatbot for Customer Support}, booktitle = {Increasing Naturalness and Flexibility in Spoken Dialogue Interaction - 10th International Workshop on Spoken Dialogue Systems, {IWSDS} 2019, Syracuse, Sicily, Italy, 24-26 April 2019}, series = {Lecture Notes in Electrical Engineering}, volume = {714}, pages = {251--259}, publisher = {Springer}, year = {2019}, url = {https://doi.org/10.1007/978-981-15-9323-9\_21}, doi = {10.1007/978-981-15-9323-9\_21}, timestamp = {Sun, 14 Mar 2021 11:38:06 +0100}, biburl = {https://dblp.org/rec/conf/iwsds/VuKSB19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-02546, author = {Wei Rao and Chenglin Xu and Eng Siong Chng and Haizhou Li}, title = {Target Speaker Extraction for Overlapped Multi-Talker Speaker Verification}, journal = {CoRR}, volume = {abs/1902.02546}, year = {2019}, url = {http://arxiv.org/abs/1902.02546}, eprinttype = {arXiv}, eprint = {1902.02546}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-02546.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-03705, author = {Xiaohai Tian and Eng Siong Chng and Haizhou Li}, title = {A Vocoder-free WaveNet Voice Conversion with Non-Parallel Data}, journal = {CoRR}, volume = {abs/1902.03705}, year = {2019}, url = {http://arxiv.org/abs/1902.03705}, eprinttype = {arXiv}, eprint = {1902.03705}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-03705.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1903-09952, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, title = {Optimization of Speaker Extraction Neural Network with Magnitude and Temporal Spectrum Approximation Loss}, journal = {CoRR}, volume = {abs/1903.09952}, year = {2019}, url = {http://arxiv.org/abs/1903.09952}, eprinttype = {arXiv}, eprint = {1903.09952}, timestamp = {Tue, 02 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1903-09952.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-03799, author = {Yerbolat Khassanov and Zhiping Zeng and Van Tung Pham and Haihua Xu and Eng Siong Chng}, title = {Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation}, journal = {CoRR}, volume = {abs/1904.03799}, year = {2019}, url = {http://arxiv.org/abs/1904.03799}, eprinttype = {arXiv}, eprint = {1904.03799}, timestamp = {Thu, 25 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-03799.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-03802, author = {Yerbolat Khassanov and Haihua Xu and Van Tung Pham and Zhiping Zeng and Eng Siong Chng and Chongjia Ni and Bin Ma}, title = {Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data}, journal = {CoRR}, volume = {abs/1904.03802}, year = {2019}, url = {http://arxiv.org/abs/1904.03802}, eprinttype = {arXiv}, eprint = {1904.03802}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-03802.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-07386, author = {Kong Aik Lee and Ville Hautam{\"{a}}ki and Tomi Kinnunen and Hitoshi Yamamoto and Koji Okabe and Ville Vestman and Jing Huang and Guohong Ding and Hanwu Sun and Anthony Larcher and Rohan Kumar Das and Haizhou Li and Mickael Rouvier and Pierre{-}Michel Bousquet and Wei Rao and Qing Wang and Chunlei Zhang and Fahimeh Bahmaninezhad and H{\'{e}}ctor Delgado and Jose Patino and Qiongqiong Wang and Ling Guo and Takafumi Koshinaka and Jiacen Zhang and Koichi Shinoda and Trung Ngo Trong and Md. Sahidullah and Fan Lu and Yun Tang and Ming Tu and Kah Kuan Teh and Tran Huy Dat and Kuruvachan K. George and Ivan Kukanov and Florent Desnous and Jichen Yang and Emre Yilmaz and Longting Xu and Jean{-}Fran{\c{c}}ois Bonastre and Chenglin Xu and Zhi Hao Lim and Eng Siong Chng and Shivesh Ranjan and John H. L. Hansen and Massimiliano Todisco and Nicholas W. D. Evans}, title = {{I4U} Submission to {NIST} {SRE} 2018: Leveraging from a Decade of Shared Experiences}, journal = {CoRR}, volume = {abs/1904.07386}, year = {2019}, url = {http://arxiv.org/abs/1904.07386}, eprinttype = {arXiv}, eprint = {1904.07386}, timestamp = {Thu, 14 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-07386.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1912-00863, author = {Van Tung Pham and Haihua Xu and Yerbolat Khassanov and Zhiping Zeng and Eng Siong Chng and Chongjia Ni and Bin Ma and Haizhou Li}, title = {Independent language modeling architecture for end-to-end {ASR}}, journal = {CoRR}, volume = {abs/1912.00863}, year = {2019}, url = {http://arxiv.org/abs/1912.00863}, eprinttype = {arXiv}, eprint = {1912.00863}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1912-00863.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/sigpro/YuXXC18, author = {Jia Yu and Lei Xie and Xiong Xiao and Eng Siong Chng}, title = {Learning distributed sentence representations for story segmentation}, journal = {Signal Process.}, volume = {142}, pages = {403--411}, year = {2018}, url = {https://doi.org/10.1016/j.sigpro.2017.07.026}, doi = {10.1016/J.SIGPRO.2017.07.026}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/sigpro/YuXXC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/speech/PhamXXCCL18, author = {Van Tung Pham and Haihua Xu and Xiong Xiao and Nancy F. Chen and Eng Siong Chng and Haizhou Li}, title = {Re-ranking spoken term detection with acoustic exemplars of keywords}, journal = {Speech Commun.}, volume = {104}, pages = {12--23}, year = {2018}, url = {https://doi.org/10.1016/j.specom.2018.09.004}, doi = {10.1016/J.SPECOM.2018.09.004}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/speech/PhamXXCCL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aclnews/LiWACL18, author = {Zhongwei Li and Xuancong Wang and AiTi Aw and Eng Siong Chng and Haizhou Li}, editor = {Nancy F. Chen and Rafael E. Banchs and Xiangyu Duan and Min Zhang and Haizhou Li}, title = {Named-Entity Tagging and Domain adaptation for Better Customized Translation}, booktitle = {Proceedings of the Seventh Named Entities Workshop, NEWS@ACL 2018, Melbourne, Australia, July 20, 2018}, pages = {41--46}, publisher = {Association for Computational Linguistics}, year = {2018}, url = {https://doi.org/10.18653/v1/w18-2407}, doi = {10.18653/V1/W18-2407}, timestamp = {Fri, 06 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aclnews/LiWACL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/CanHC18, author = {Duy{-}Cat Can and Thi{-}Nga Ho and Eng Siong Chng}, editor = {Minghui Dong and Moch Arif Bijaksana and Herry Sujaini and Ade Romadhony and Fariska Z. Ruskanda and Elvira Nurfadhilah and Lyla Ruslana Aini}, title = {A Hybrid Deep Learning Architecture for Sentence Unit Detection}, booktitle = {2018 International Conference on Asian Language Processing, {IALP} 2018, Bandung, Indonesia, November 15-17, 2018}, pages = {129--132}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/IALP.2018.8629178}, doi = {10.1109/IALP.2018.8629178}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ialp/CanHC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/HoCC18, author = {Thi{-}Nga Ho and Duy{-}Cat Can and Engsiong Chng}, editor = {Minghui Dong and Moch Arif Bijaksana and Herry Sujaini and Ade Romadhony and Fariska Z. Ruskanda and Elvira Nurfadhilah and Lyla Ruslana Aini}, title = {An Investigation of Word Embeddings with Deep Bidirectional {LSTM} for Sentence Unit Detection in Automatic Speech Transcription}, booktitle = {2018 International Conference on Asian Language Processing, {IALP} 2018, Bandung, Indonesia, November 15-17, 2018}, pages = {139--142}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/IALP.2018.8629114}, doi = {10.1109/IALP.2018.8629114}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ialp/HoCC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuRXC018, author = {Chenglin Xu and Wei Rao and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {Single Channel Speech Separation with Constrained Utterance Level Permutation Invariant Training Using Grid {LSTM}}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {6--10}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8462471}, doi = {10.1109/ICASSP.2018.8462471}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XuRXC018.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangRSXCL18, author = {Qing Wang and Wei Rao and Sining Sun and Lei Xie and Eng Siong Chng and Haizhou Li}, title = {Unsupervised Domain Adaptation via Domain Adversarial Training for Speaker Recognition}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {4889--4893}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8461423}, doi = {10.1109/ICASSP.2018.8461423}, timestamp = {Fri, 10 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/WangRSXCL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuPKLCL18, author = {Haihua Xu and Van Tung Pham and Zin Tun Kyaw and Zhi Hao Lim and Eng Siong Chng and Haizhou Li}, editor = {B. Yegnanarayana}, title = {Mandarin-English Code-switching Speech Recognition}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {554--555}, publisher = {{ISCA}}, year = {2018}, url = {https://www.isca-speech.org/archive/interspeech\_2018/xu18d\_interspeech.html}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuPKLCL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GuoXXC18, author = {Pengcheng Guo and Haihua Xu and Lei Xie and Eng Siong Chng}, editor = {B. Yegnanarayana}, title = {Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {1928--1932}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1974}, doi = {10.21437/INTERSPEECH.2018-1974}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/GuoXXC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/KhassanovC18, author = {Yerbolat Khassanov and Eng Siong Chng}, editor = {B. Yegnanarayana}, title = {Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in {ASR}}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {3343--3347}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1021}, doi = {10.21437/INTERSPEECH.2018-1021}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/KhassanovC18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuRCL18, author = {Chenglin Xu and Wei Rao and Eng Siong Chng and Haizhou Li}, editor = {B. Yegnanarayana}, title = {A Shifted Delta Coefficient Objective for Monaural Speech Separation Using Multi-task Learning}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {3479--3483}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1150}, doi = {10.21437/INTERSPEECH.2018-1150}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/XuRCL18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/odyssey/TianWXC018, author = {Xiaohai Tian and Junchao Wang and Haihua Xu and Eng Siong Chng and Haizhou Li}, editor = {Anthony Larcher and Jean{-}Fran{\c{c}}ois Bonastre}, title = {Average Modeling Approach to Voice Conversion with Non-Parallel Data}, booktitle = {Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29 June 2018, Les Sables d'Olonne, France}, pages = {227--232}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Odyssey.2018-32}, doi = {10.21437/ODYSSEY.2018-32}, timestamp = {Tue, 16 Nov 2021 11:36:04 +0100}, biburl = {https://dblp.org/rec/conf/odyssey/TianWXC018.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-06200, author = {Pengcheng Guo and Haihua Xu and Lei Xie and Eng Siong Chng}, title = {Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition}, journal = {CoRR}, volume = {abs/1806.06200}, year = {2018}, url = {http://arxiv.org/abs/1806.06200}, eprinttype = {arXiv}, eprint = {1806.06200}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-06200.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-10306, author = {Yerbolat Khassanov and Eng Siong Chng}, title = {Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in {ASR}}, journal = {CoRR}, volume = {abs/1806.10306}, year = {2018}, url = {http://arxiv.org/abs/1806.10306}, eprinttype = {arXiv}, eprint = {1806.10306}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-10306.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-00241, author = {Zhiping Zeng and Yerbolat Khassanov and Van Tung Pham and Haihua Xu and Eng Siong Chng and Haizhou Li}, title = {On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition}, journal = {CoRR}, volume = {abs/1811.00241}, year = {2018}, url = {http://arxiv.org/abs/1811.00241}, eprinttype = {arXiv}, eprint = {1811.00241}, timestamp = {Thu, 22 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-00241.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jaihc/YuXXC17, author = {Jia Yu and Lei Xie and Xiong Xiao and Eng Siong Chng}, title = {A hybrid neural network hidden Markov model approach for automatic story segmentation}, journal = {J. Ambient Intell. Humaniz. Comput.}, volume = {8}, number = {6}, pages = {925--936}, year = {2017}, url = {https://doi.org/10.1007/s12652-017-0501-9}, doi = {10.1007/S12652-017-0501-9}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jaihc/YuXXC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/TianLWCL17, author = {Xiaohai Tian and Siu Wa Lee and Zhizheng Wu and Eng Siong Chng and Haizhou Li}, title = {An Exemplar-Based Approach to Frequency Warping for Voice Conversion}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {25}, number = {10}, pages = {1863--1876}, year = {2017}, url = {https://doi.org/10.1109/TASLP.2017.2723721}, doi = {10.1109/TASLP.2017.2723721}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/TianLWCL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aciids/KhassanovCBC17, author = {Yerbolat Khassanov and Tze Yuang Chong and Benjamin Bigot and Eng Siong Chng}, editor = {Ngoc Thanh Nguyen and Satoshi Tojo and Le Minh Nguyen and Bogdan Trawinski}, title = {Unsupervised Language Model Adaptation by Data Selection for Speech Recognition}, booktitle = {Intelligent Information and Database Systems - 9th Asian Conference, {ACIIDS} 2017, Kanazawa, Japan, April 3-5, 2017, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {10191}, pages = {508--517}, year = {2017}, url = {https://doi.org/10.1007/978-3-319-54472-4\_48}, doi = {10.1007/978-3-319-54472-4\_48}, timestamp = {Thu, 16 Mar 2023 20:00:29 +0100}, biburl = {https://dblp.org/rec/conf/aciids/KhassanovCBC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/YuXXC17, author = {Jia Yu and Lei Xie and Xiong Xiao and Eng Siong Chng}, title = {An end-to-end neural network approach to story segmentation}, booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia, December 12-15, 2017}, pages = {171--176}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/APSIPA.2017.8282023}, doi = {10.1109/APSIPA.2017.8282023}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/YuXXC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/ChenLDPNXHCXSCM17, author = {Nancy F. Chen and Boon Pang Lim and Van Hai Do and Van Tung Pham and Chongjia Ni and Haihua Xu and Mark Hasegawa{-}Johnson and Wenda Chen and Xiong Xiao and Sunil Sivadas and Eng Siong Chng and Bin Ma and Haizhou Li}, title = {Low-resource spoken keyword search strategies in georgian inspired by distinctive feature theory}, booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia, December 12-15, 2017}, pages = {1322--1327}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/APSIPA.2017.8282237}, doi = {10.1109/APSIPA.2017.8282237}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/ChenLDPNXHCXSCM17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/LimTRC17, author = {Zhi Hao Lim and Xiaohai Tian and Wei Rao and Eng Siong Chng}, title = {An investigation of spectral feature partitioning for replay attacks detection}, booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia, December 12-15, 2017}, pages = {1570--1573}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/APSIPA.2017.8282273}, doi = {10.1109/APSIPA.2017.8282273}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/LimTRC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/ZengXCCL17, author = {Zhiping Zeng and Haihua Xu and Tze Yuang Chong and Eng Siong Chng and Haizhou Li}, title = {Improving N-gram language modeling for code-switching speech recognition}, booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia, December 12-15, 2017}, pages = {1596--1601}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/APSIPA.2017.8282279}, doi = {10.1109/APSIPA.2017.8282279}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/ZengXCCL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/YuXXC17a, author = {Jia Yu and Xiong Xiao and Lei Xie and Eng Siong Chng}, title = {Topic embedding of sentences for story segmentation}, booktitle = {2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} {ASC} 2017, Kuala Lumpur, Malaysia, December 12-15, 2017}, pages = {1602--1607}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/APSIPA.2017.8282280}, doi = {10.1109/APSIPA.2017.8282280}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/YuXXC17a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hci/TianMLSCLGM17, author = {Xiaohai Tian and Lei Meng and Siyuan Liu and Zhiqi Shen and Eng Siong Chng and Cyril Leung and Frank Guan and Chunyan Miao}, editor = {Jia Zhou and Gavriel Salvendy}, title = {Novel Functional Technologies for Age-Friendly E-commerce}, booktitle = {Human Aspects of {IT} for the Aged Population. Applications, Services and Contexts - Third International Conference, {ITAP} 2017, Held as Part of {HCI} International 2017, Vancouver, BC, Canada, July 9-14, 2017, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {10298}, pages = {150--158}, publisher = {Springer}, year = {2017}, url = {https://doi.org/10.1007/978-3-319-58536-9\_13}, doi = {10.1007/978-3-319-58536-9\_13}, timestamp = {Tue, 24 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hci/TianMLSCLGM17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/HouTCML17, author = {Nana Hou and Xiaohai Tian and Eng Siong Chng and Bin Ma and Haizhou Li}, editor = {Rong Tong and Yue Zhang and Yanfeng Lu and Minghui Dong}, title = {Improving air traffic control speech intelligibility by reducing speaking rate effectively}, booktitle = {2017 International Conference on Asian Language Processing, {IALP} 2017, Singapore, December 5-7, 2017}, pages = {197--200}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IALP.2017.8300578}, doi = {10.1109/IALP.2017.8300578}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ialp/HouTCML17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/LeeHCL17, author = {Grandee Lee and Thi{-}Nga Ho and Eng Siong Chng and Haizhou Li}, editor = {Rong Tong and Yue Zhang and Yanfeng Lu and Minghui Dong}, title = {A review of the mandarin-english code-switching corpus: {SEAME}}, booktitle = {2017 International Conference on Asian Language Processing, {IALP} 2017, Singapore, December 5-7, 2017}, pages = {210--213}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IALP.2017.8300581}, doi = {10.1109/IALP.2017.8300581}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ialp/LeeHCL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/LiCL17, author = {Zhongwei Li and Eng Siong Chng and Haizhou Li}, editor = {Rong Tong and Yue Zhang and Yanfeng Lu and Minghui Dong}, title = {Named entity transliteration with sequence-to-sequence neural network}, booktitle = {2017 International Conference on Asian Language Processing, {IALP} 2017, Singapore, December 5-7, 2017}, pages = {374--378}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IALP.2017.8300621}, doi = {10.1109/IALP.2017.8300621}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ialp/LiCL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoZJCL17, author = {Xiong Xiao and Shengkui Zhao and Douglas L. Jones and Eng Siong Chng and Haizhou Li}, title = {On time-frequency mask estimation for {MVDR} beamforming with application in robust speech recognition}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {3246--3250}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7952756}, doi = {10.1109/ICASSP.2017.7952756}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XiaoZJCL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iccse/MengHTSCGML17, author = {Lei Meng and Nguyen Quy Hy and Xiaohai Tian and Zhiqi Shen and Eng Siong Chng and Frank Yunqing Guan and Chunyan Miao and Cyril Leung}, title = {Towards Age-friendly E-commerce Through Crowd-Improved Speech Recognition, Multimodal Search, and Personalized Speech Feedback}, booktitle = {Proceedings of the 2nd International Conference on Crowd Science and Engineering, {ICCSE} 2017, Beijing, China, July 06 - 09, 2017}, pages = {127--135}, publisher = {{ACM}}, year = {2017}, url = {https://doi.org/10.1145/3126973.3129306}, doi = {10.1145/3126973.3129306}, timestamp = {Tue, 24 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iccse/MengHTSCGML17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LeeHKLa17, author = {Kong{-}Aik Lee and Ville Hautam{\"{a}}ki and Tomi Kinnunen and Anthony Larcher and Chunlei Zhang and Andreas Nautsch and Themos Stafylakis and Gang Liu and Micka{\"{e}}l Rouvier and Wei Rao and Federico Alegre and J. Ma and Man{-}Wai Mak and Achintya Kumar Sarkar and H{\'{e}}ctor Delgado and Rahim Saeidi and Hagai Aronowitz and Aleksandr Sizov and Hanwu Sun and Trung Hieu Nguyen and G. Wang and Bin Ma and Ville Vestman and Md. Sahidullah and M. Halonen and Anssi Kanervisto and Ga{\"{e}}l Le Lan and Fahimeh Bahmaninezhad and Sergey Isadskiy and Christian Rathgeb and Christoph Busch and Georgios Tzimiropoulos and Q. Qian and Z. Wang and Q. Zhao and T. Wang and H. Li and J. Xue and S. Zhu and R. Jin and T. Zhao and Pierre{-}Michel Bousquet and Moez Ajili and Waad Ben Kheder and Driss Matrouf and Zhi Hao Lim and Chenglin Xu and Haihua Xu and Xiong Xiao and Eng Siong Chng and Benoit G. B. Fauve and Kaavya Sriskandaraja and Vidhyasaharan Sethu and W. W. Lin and Dennis Alexander Lehmann Thomsen and Zheng{-}Hua Tan and Massimiliano Todisco and Nicholas W. D. Evans and Haizhou Li and John H. L. Hansen and Jean{-}Fran{\c{c}}ois Bonastre and Eliathamby Ambikairajah}, editor = {Francisco Lacerda}, title = {The {I4U} Mega Fusion and Collaboration for {NIST} Speaker Recognition Evaluation 2016}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {1328--1332}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-203}, doi = {10.21437/INTERSPEECH.2017-203}, timestamp = {Thu, 29 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LeeHKLa17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuXSRCL17, author = {Chenglin Xu and Xiong Xiao and Sining Sun and Wei Rao and Eng Siong Chng and Haizhou Li}, editor = {Francisco Lacerda}, title = {Weighted Spatial Covariance Matrix Estimation for {MUSIC} Based {TDOA} Estimation of Speech Source}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {1894--1898}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-199}, doi = {10.21437/INTERSPEECH.2017-199}, timestamp = {Sun, 06 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuXSRCL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/soict/PhamXXCC17, author = {Van Tung Pham and Haihua Xu and Xiong Xiao and Nancy F. Chen and Eng Siong Chng}, title = {Pruning Strategies for Partial Search in Spoken Term Detection}, booktitle = {Proceedings of the Eighth International Symposium on Information and Communication Technology, Nha Trang City, Viet Nam, December 7-8, 2017}, pages = {114--119}, publisher = {{ACM}}, year = {2017}, url = {https://doi.org/10.1145/3155133.3155164}, doi = {10.1145/3155133.3155164}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/soict/PhamXXCC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ejasp/XiaoZNZJCL16, author = {Xiong Xiao and Shengkui Zhao and Duc Hoang Ha Nguyen and Xionghu Zhong and Douglas L. Jones and Eng Siong Chng and Haizhou Li}, title = {Speech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation}, journal = {{EURASIP} J. Adv. Signal Process.}, volume = {2016}, pages = {4}, year = {2016}, url = {https://doi.org/10.1186/s13634-015-0300-4}, doi = {10.1186/S13634-015-0300-4}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ejasp/XiaoZNZJCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/mta/HyLTDC16, author = {Nguyen Quy Hy and Siu Wa Lee and Xiaohai Tian and Minghui Dong and Eng Siong Chng}, title = {High quality voice conversion using prosodic and high-resolution spectral features}, journal = {Multim. Tools Appl.}, volume = {75}, number = {9}, pages = {5265--5285}, year = {2016}, url = {https://doi.org/10.1007/s11042-015-3039-x}, doi = {10.1007/S11042-015-3039-X}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/mta/HyLTDC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/NguyenXCL16, author = {Duc Hoang Ha Nguyen and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {Feature Adaptation Using Linear Spectro-Temporal Transform for Robust Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {24}, number = {6}, pages = {1006--1019}, year = {2016}, url = {https://doi.org/10.1109/TASLP.2016.2522646}, doi = {10.1109/TASLP.2016.2522646}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/NguyenXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/vlsisp/UedaWKXCL16, author = {Yuma Ueda and Longbiao Wang and Atsuhiko Kai and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Single-channel Dereverberation for Distant-Talking Speech Recognition by Combining Denoising Autoencoder and Temporal Structure Normalization}, journal = {J. Signal Process. Syst.}, volume = {82}, number = {2}, pages = {151--161}, year = {2016}, url = {https://doi.org/10.1007/s11265-015-1007-3}, doi = {10.1007/S11265-015-1007-3}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/vlsisp/UedaWKXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aciids/HoCDPC16, author = {Thi{-}Nga Ho and Tze Yuang Chong and Van Hai Do and Van Tung Pham and Eng Siong Chng}, editor = {Ngoc Thanh Nguyen and Bogdan Trawinski and Hamido Fujita and Tzung{-}Pei Hong}, title = {Improving Efficiency of Sentence Boundary Detection by Feature Selection}, booktitle = {Intelligent Information and Database Systems - 8th Asian Conference, {ACIIDS} 2016, Da Nang, Vietnam, March 14-16, 2016, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {9622}, pages = {594--603}, publisher = {Springer}, year = {2016}, url = {https://doi.org/10.1007/978-3-662-49390-8\_58}, doi = {10.1007/978-3-662-49390-8\_58}, timestamp = {Thu, 16 Mar 2023 20:00:29 +0100}, biburl = {https://dblp.org/rec/conf/aciids/HoCDPC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/LeowCL16, author = {Su Jun Leow and Eng Siong Chng and Chin{-}Hui Lee}, title = {Zero resource anti-spoofing detection for unit selection based synthetic speech using image spectrogram artifacts}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December 13-16, 2016}, pages = {1--6}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/APSIPA.2016.7820863}, doi = {10.1109/APSIPA.2016.7820863}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/LeowCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/TianXCL16, author = {Xiaohai Tian and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {Spoofing speech detection using temporal convolutional neural network}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December 13-16, 2016}, pages = {1--6}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/APSIPA.2016.7820738}, doi = {10.1109/APSIPA.2016.7820738}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/TianXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/XiaoWCL16, author = {Xiong Xiao and Shinji Watanabe and Eng Siong Chng and Haizhou Li}, title = {Beamforming networks using spatial covariance features for far-field speech recognition}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December 13-16, 2016}, pages = {1--6}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/APSIPA.2016.7820724}, doi = {10.1109/APSIPA.2016.7820724}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/XiaoWCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/XuRXHCL16, author = {Haihua Xu and Wei Rao and Xiong Xiao and Hao Huang and Eng Siong Chng and Haizhou Li}, title = {I-vector based deep neural network acoustic model adaptation using multilingual language resource}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2016, Jeju, South Korea, December 13-16, 2016}, pages = {1--5}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/APSIPA.2016.7820698}, doi = {10.1109/APSIPA.2016.7820698}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/XuRXHCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/VuBC16, author = {Thanh T. Vu and Benjamin Bigot and Eng Siong Chng}, title = {Combining non-negative matrix factorization and deep neural networks for speech enhancement and automatic speech recognition}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {499--503}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7471725}, doi = {10.1109/ICASSP.2016.7471725}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/VuBC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TianWXCL16, author = {Xiaohai Tian and Zhizheng Wu and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {Spoofing detection from a feature representation perspective}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {2119--2123}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472051}, doi = {10.1109/ICASSP.2016.7472051}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/TianWXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenLCMLD16, author = {Liping Chen and Kong{-}Aik Lee and Eng Siong Chng and Bin Ma and Haizhou Li and Li{-}Rong Dai}, title = {Content-aware local variability vector for speaker verification with short utterance}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {5485--5489}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472726}, doi = {10.1109/ICASSP.2016.7472726}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenLCMLD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuHXPLWDLXMCL16, author = {Haihua Xu and Jingyong Hou and Xiong Xiao and Van Tung Pham and Cheung{-}Chi Leung and Lei Wang and Van Hai Do and Hang Lv and Lei Xie and Bin Ma and Eng Siong Chng and Haizhou Li}, title = {Approximate search of audio queries by using {DTW} with phone time boundary and data augmentation}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {6030--6034}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472835}, doi = {10.1109/ICASSP.2016.7472835}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XuHXPLWDLXMCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/PhamXXCCL16, author = {Van Tung Pham and Haihua Xu and Xiong Xiao and Nancy F. Chen and Eng Siong Chng and Haizhou Li}, title = {Keyword search using query expansion for graph-based rescoring of hypothesized detections}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {6035--6039}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472836}, doi = {10.1109/ICASSP.2016.7472836}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/PhamXXCCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenPXXDNCSLCML16, author = {Nancy F. Chen and Van Tung Pham and Haihua Xu and Xiong Xiao and Van Hai Do and Chongjia Ni and I{-}Fan Chen and Sunil Sivadas and Chin{-}Hui Lee and Eng Siong Chng and Bin Ma and Haizhou Li}, title = {Exemplar-inspired strategies for low-resource spoken keyword search in Swahili}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {6040--6044}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472837}, doi = {10.1109/ICASSP.2016.7472837}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenPXXDNCSLCML16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoZNJCL16, author = {Xiong Xiao and Shengkui Zhao and Thi Ngoc Tho Nguyen and Douglas L. Jones and Eng Siong Chng and Haizhou Li}, title = {An expectation-maximization eigenvector clustering approach to direction of arrival estimation of multiple speech sources}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {6330--6334}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472895}, doi = {10.1109/ICASSP.2016.7472895}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XiaoZNJCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/PhamXXCCL16, author = {Van Tung Pham and Haihua Xu and Xiong Xiao and Nancy F. Chen and Eng Siong Chng and Haizhou Li}, editor = {Nelson Morgan}, title = {Rescoring Hypothesized Detections of Out-of-Vocabulary Keywords Using Subword Samples}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {933--937}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-646}, doi = {10.21437/INTERSPEECH.2016-646}, timestamp = {Mon, 26 Jun 2023 16:43:56 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/PhamXXCCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuSNXHCL16, author = {Haihua Xu and Hang Su and Chongjia Ni and Xiong Xiao and Hao Huang and Eng Siong Chng and Haizhou Li}, editor = {Nelson Morgan}, title = {Semi-Supervised and Cross-Lingual Knowledge Transfer Learnings for {DNN} Hybrid Acoustic Models Under Low-Resource Conditions}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {1315--1319}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-1099}, doi = {10.21437/INTERSPEECH.2016-1099}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/XuSNXHCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/YuXXCL16, author = {Jia Yu and Xiong Xiao and Lei Xie and Eng Siong Chng and Haizhou Li}, editor = {Nelson Morgan}, title = {A {DNN-HMM} Approach to Story Segmentation}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {1527--1531}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-873}, doi = {10.21437/INTERSPEECH.2016-873}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/YuXXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TianWXCL16, author = {Xiaohai Tian and Zhizheng Wu and Xiong Xiao and Eng Siong Chng and Haizhou Li}, editor = {Nelson Morgan}, title = {An Investigation of Spoofing Speech Detection Under Additive Noise and Reverberant Conditions}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {1715--1719}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-743}, doi = {10.21437/INTERSPEECH.2016-743}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/TianWXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LeeLDHRXLSNWSCK16, author = {Kong{-}Aik Lee and Haizhou Li and Li Deng and Ville Hautam{\"{a}}ki and Wei Rao and Xiong Xiao and Anthony Larcher and Hanwu Sun and Trung Hieu Nguyen and Guangsen Wang and Aleksandr Sizov and Jianshu Chen and Ivan Kukanov and Amir Hossein Poorjam and Trung Ngo Trong and Chenglin Xu and Haihua Xu and Bin Ma and Eng Siong Chng and Sylvain Meignier}, editor = {Nelson Morgan}, title = {The 2015 {NIST} Language Recognition Evaluation: The Shared View of I2R, Fantastic4 and SingaMS}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {3211--3215}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-624}, doi = {10.21437/INTERSPEECH.2016-624}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LeeLDHRXLSNWSCK16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LeungWXHPLXXNMC16, author = {Cheung{-}Chi Leung and Lei Wang and Haihua Xu and Jingyong Hou and Van Tung Pham and Hang Lv and Lei Xie and Xiong Xiao and Chongjia Ni and Bin Ma and Eng Siong Chng and Haizhou Li}, editor = {Nelson Morgan}, title = {Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {3703--3707}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-691}, doi = {10.21437/INTERSPEECH.2016-691}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LeungWXHPLXXNMC16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/RaoXXXLCL16, author = {Wei Rao and Xiong Xiao and Chenglin Xu and Haihua Xu and Kong{-}Aik Lee and Eng Siong Chng and Haizhou Li}, title = {Neural networks based channel compensation for i-vector speaker verification}, booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016}, pages = {1--5}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ISCSLP.2016.7918436}, doi = {10.1109/ISCSLP.2016.7918436}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/RaoXXXLCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/ZhangXWDICL16, author = {Zhaofeng Zhang and Xiong Xiao and Longbiao Wang and Jianwu Dang and Masahiro Iwahashi and Eng Siong Chng and Haizhou Li}, title = {Multi-channel feature adaptation for robust speech recognition}, booktitle = {10th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2016, Tianjin, China, October 17-20, 2016}, pages = {1--5}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ISCSLP.2016.7918435}, doi = {10.1109/ISCSLP.2016.7918435}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/ZhangXWDICL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mediaeval/WangNLYXXXNCML16, author = {Lei Wang and Chongjia Ni and Cheung{-}Chi Leung and Changhuai You and Lei Xie and Haihua Xu and Xiong Xiao and Tin Lay Nwe and Eng Siong Chng and Bin Ma and Haizhou Li}, editor = {Guillaume Gravier and Claire{-}H{\'{e}}l{\`{e}}ne Demarty and Herv{\'{e}} Bredin and Bogdan Ionescu and Christina Boididou and Emmanuel Dellandr{\'{e}}a and Jaeyoung Choi and Michael Riegler and Richard F. E. Sutcliffe and Igor Sz{\"{o}}ke and Gareth J. F. Jones and Martha A. Larson}, title = {The {NNI} Vietnamese Speech Recognition System for MediaEval 2016}, booktitle = {Working Notes Proceedings of the MediaEval 2016 Workshop, Hilversum, The Netherlands, October 20-21, 2016}, series = {{CEUR} Workshop Proceedings}, volume = {1739}, publisher = {CEUR-WS.org}, year = {2016}, url = {https://ceur-ws.org/Vol-1739/MediaEval\_2016\_paper\_52.pdf}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mediaeval/WangNLYXXXNCML16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/TianWXCL16, author = {Xiaohai Tian and Zhizheng Wu and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {Spoofing detection under noisy conditions: a preliminary investigation and an initial database}, journal = {CoRR}, volume = {abs/1602.02950}, year = {2016}, url = {http://arxiv.org/abs/1602.02950}, eprinttype = {arXiv}, eprint = {1602.02950}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/TianWXCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/ZhangXWCL16, author = {Zhaofeng Zhang and Xiong Xiao and Longbiao Wang and Eng Siong Chng and Haizhou Li}, title = {Noise Robust Speech Recognition Using Multi-Channel Based Channel Selection And ChannelWeighting}, journal = {CoRR}, volume = {abs/1604.03276}, year = {2016}, url = {http://arxiv.org/abs/1604.03276}, eprinttype = {arXiv}, eprint = {1604.03276}, timestamp = {Wed, 12 Sep 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/ZhangXWCL16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jclc/DoXCL15, author = {Van Hai Do and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Context-dependent Phone Mapping for Acoustic Modeling of Under-resourced Languages}, journal = {Int. J. Asian Lang. Process.}, volume = {23}, number = {1}, pages = {21--33}, year = {2015}, url = {http://www.colips.org/journal/volume23/23.1.2\_VanHaiDO\_IJALP.pdf}, timestamp = {Tue, 31 Mar 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jclc/DoXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/lre/LyuTCL15, author = {Dau{-}Cheng Lyu and Tien Ping Tan and Engsiong Chng and Haizhou Li}, title = {Mandarin-English code-switching speech corpus in South-East Asia: {SEAME}}, journal = {Lang. Resour. Evaluation}, volume = {49}, number = {3}, pages = {581--600}, year = {2015}, url = {https://doi.org/10.1007/s10579-015-9303-x}, doi = {10.1007/S10579-015-9303-X}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/lre/LyuTCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/mta/WuCL15, author = {Zhizheng Wu and Engsiong Chng and Haizhou Li}, title = {Exemplar-based voice conversion using joint nonnegative matrix factorization}, journal = {Multim. Tools Appl.}, volume = {74}, number = {22}, pages = {9943--9958}, year = {2015}, url = {https://doi.org/10.1007/s11042-014-2180-2}, doi = {10.1007/S11042-014-2180-2}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/mta/WuCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/ChongBCL15, author = {Tze Yuang Chong and Rafael E. Banchs and Engsiong Chng and Haizhou Li}, title = {Decoupling Word-Pair Distance and Co-occurrence Information for Effective Long History Context Language Modeling}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {23}, number = {7}, pages = {1221--1232}, year = {2015}, url = {https://doi.org/10.1109/TASLP.2015.2425223}, doi = {10.1109/TASLP.2015.2425223}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/ChongBCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/DoXCL15, author = {Van Hai Do and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {Distance metric learning for kernel density-based acoustic model under limited training data conditions}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015}, pages = {54--58}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/APSIPA.2015.7415373}, doi = {10.1109/APSIPA.2015.7415373}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/DoXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/YuXXCL15, author = {Jia Yu and Lei Xie and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {A density peak clustering approach to unsupervised acoustic subword units discovery}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015}, pages = {178--183}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/APSIPA.2015.7415498}, doi = {10.1109/APSIPA.2015.7415498}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/YuXXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/ZhangHXCLD15, author = {Shaofei Zhang and Dong{-}Yan Huang and Lei Xie and Eng Siong Chng and Haizhou Li and Minghui Dong}, title = {Non-negative matrix factorization using stable alternating direction method of multipliers for source separation}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015}, pages = {222--228}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/APSIPA.2015.7415508}, doi = {10.1109/APSIPA.2015.7415508}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/ZhangHXCLD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/PhamXDCXCL15, author = {Van Tung Pham and Haihua Xu and Van Hai Do and Tze Yuang Chong and Xiong Xiao and Eng Siong Chng and Haizhou Li}, title = {On the study of very low-resource language keyword search}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015}, pages = {358--364}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/APSIPA.2015.7415294}, doi = {10.1109/APSIPA.2015.7415294}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/PhamXDCXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/DoXXCL15, author = {Van Hai Do and Xiong Xiao and Haihua Xu and Eng Siong Chng and Haizhou Li}, title = {Multilingual exemplar-based acoustic model for the {NIST} Open {KWS} 2015 evaluation}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2015, Hong Kong, December 16-19, 2015}, pages = {594--98}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/APSIPA.2015.7415338}, doi = {10.1109/APSIPA.2015.7415338}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/DoXXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/VuBC15, author = {Thanh T. Vu and Benjamin Bigot and Engsiong Chng}, title = {Speech enhancement using beamforming and non negative matrix factorization for robust speech recognition in the CHiME-3 challenge}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {423--429}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404826}, doi = {10.1109/ASRU.2015.7404826}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/VuBC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/ZhaoXZNZRWJCL15, author = {Shengkui Zhao and Xiong Xiao and Zhaofeng Zhang and Thi Ngoc Tho Nguyen and Xionghu Zhong and Bo Ren and Longbiao Wang and Douglas L. Jones and Engsiong Chng and Haizhou Li}, title = {Robust speech recognition using beamforming with adaptive microphone gains and multichannel noise reduction}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {460--467}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404831}, doi = {10.1109/ASRU.2015.7404831}, timestamp = {Fri, 03 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/ZhaoXZNZRWJCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/XuXCL15, author = {Haihua Xu and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {On statistical machine translation method for lexicon refinement in speech recognition}, booktitle = {{IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015}, pages = {25--29}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ChinaSIP.2015.7230355}, doi = {10.1109/CHINASIP.2015.7230355}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/XuXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/TianDXXCL15, author = {Xiaohai Tian and Steven Du and Xiong Xiao and Haihua Xu and Engsiong Chng and Haizhou Li}, title = {Detecting synthetic speech using long term magnitude and phase information}, booktitle = {{IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015}, pages = {611--615}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ChinaSIP.2015.7230476}, doi = {10.1109/CHINASIP.2015.7230476}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/TianDXXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/DuXC15, author = {Steven Du and Xiong Xiao and Engsiong Chng}, title = {{DNN} feature compensation for noise robust speaker verification}, booktitle = {{IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2015, Chengdu, China, July 12-15, 2015}, pages = {871--875}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ChinaSIP.2015.7230529}, doi = {10.1109/CHINASIP.2015.7230529}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/DuXC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cicling/ChikersalPCGS15, author = {Prerna Chikersal and Soujanya Poria and Erik Cambria and Alexander F. Gelbukh and Chng Eng Siong}, editor = {Alexander F. Gelbukh}, title = {Modelling Public Sentiment in Twitter: Using Linguistic Patterns to Enhance Supervised Learning}, booktitle = {Computational Linguistics and Intelligent Text Processing - 16th International Conference, CICLing 2015, Cairo, Egypt, April 14-20, 2015, Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {9042}, pages = {49--65}, publisher = {Springer}, year = {2015}, url = {https://doi.org/10.1007/978-3-319-18117-2\_4}, doi = {10.1007/978-3-319-18117-2\_4}, timestamp = {Wed, 25 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/cicling/ChikersalPCGS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoZZJCL15, author = {Xiong Xiao and Shengkui Zhao and Xionghu Zhong and Douglas L. Jones and Engsiong Chng and Haizhou Li}, title = {A learning-based approach to direction of arrival estimation in noisy and reverberant environments}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {2814--2818}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7178484}, doi = {10.1109/ICASSP.2015.7178484}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XiaoZZJCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TianWLHCD15, author = {Xiaohai Tian and Zhizheng Wu and Siu Wa Lee and Nguyen Quy Hy and Engsiong Chng and Minghui Dong}, title = {Sparse representation for frequency warping based voice conversion}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {4235--4239}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7178769}, doi = {10.1109/ICASSP.2015.7178769}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/TianWLHCD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuYXXLCYLWLMCL15, author = {Haihua Xu and Peng Yang and Xiong Xiao and Lei Xie and Cheung{-}Chi Leung and Hongjie Chen and Jia Yu and Hang Lv and Lei Wang and Su Jun Leow and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Language independent query-by-example spoken term detection using N-best phone sequences and partial matching}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5191--5195}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7178961}, doi = {10.1109/ICASSP.2015.7178961}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XuYXXLCYLWLMCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenNCSPXXLLLL015, author = {Nancy F. Chen and Chongjia Ni and I{-}Fan Chen and Sunil Sivadas and Van Tung Pham and Haihua Xu and Xiong Xiao and Tze Siong Lau and Su Jun Leow and Boon Pang Lim and Cheung{-}Chi Leung and Lei Wang and Chin{-}Hui Lee and Alvina Goh and Engsiong Chng and Bin Ma and Haizhou Li}, title = {Low-resource keyword search strategies for tamil}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5366--5370}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7178996}, doi = {10.1109/ICASSP.2015.7178996}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenNCSPXXLLLL015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LeowCL15, author = {Su Jun Leow and Engsiong Chng and Chin{-}Hui Lee}, title = {Language-resource independent speech segmentation using cues from a spectrogram image}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5813--5817}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7179086}, doi = {10.1109/ICASSP.2015.7179086}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LeowCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChongBCL15, author = {Tze Yuang Chong and Rafael E. Banchs and Engsiong Chng and Haizhou Li}, title = {{TDTO} language modeling with feedforward neural networks}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {1458--1462}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-348}, doi = {10.21437/INTERSPEECH.2015-348}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChongBCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhangHXCLD15, author = {Shaofei Zhang and Dong{-}Yan Huang and Lei Xie and Engsiong Chng and Haizhou Li and Minghui Dong}, title = {Regularized non-negative matrix factorization using alternating direction method of multipliers and its application to source separation}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {1498--1502}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-356}, doi = {10.21437/INTERSPEECH.2015-356}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ZhangHXCLD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XiaoTDXCL15, author = {Xiong Xiao and Xiaohai Tian and Steven Du and Haihua Xu and Engsiong Chng and Haizhou Li}, title = {Spoofing speech detection using high dimensional magnitude and phase features: the {NTU} approach for ASVspoof 2015 challenge}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {2052--2056}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-465}, doi = {10.21437/INTERSPEECH.2015-465}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XiaoTDXCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuDXC15, author = {Haihua Xu and Van Hai Do and Xiong Xiao and Engsiong Chng}, title = {A comparative study of {BNF} and {DNN} multilingual training on cross-lingual low-resource speech recognition}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {2132--2136}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-481}, doi = {10.21437/INTERSPEECH.2015-481}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuDXC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TianWLHDC15, author = {Xiaohai Tian and Zhizheng Wu and Siu Wa Lee and Nguyen Quy Hy and Minghui Dong and Engsiong Chng}, title = {System fusion for high-performance voice conversion}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {2759--2763}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-581}, doi = {10.21437/INTERSPEECH.2015-581}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/TianWLHDC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XiaoZZJCL15, author = {Xiong Xiao and Shengkui Zhao and Xionghu Zhong and Douglas L. Jones and Engsiong Chng and Haizhou Li}, title = {Learning to estimate reverberation time in noisy and reverberant rooms}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {3431--3435}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-680}, doi = {10.21437/INTERSPEECH.2015-680}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XiaoZZJCL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mediaeval/HouPL0XLXFNXCZS15, author = {Jingyong Hou and Van Tung Pham and Cheung{-}Chi Leung and Lei Wang and Haihua Xu and Hang Lv and Lei Xie and Zhonghua Fu and Chongjia Ni and Xiong Xiao and Hongjie Chen and Shaofei Zhang and Sining Sun and Yougen Yuan and Pengcheng Li and Tin Lay Nwe and Sunil Sivadas and Bin Ma and Engsiong Chng and Haizhou Li}, editor = {Martha A. Larson and Bogdan Ionescu and Mats Sj{\"{o}}berg and Xavier Anguera and Johann Poignant and Michael Riegler and Maria Eskevich and Claudia Hauff and Richard F. E. Sutcliffe and Gareth J. F. Jones and Yi{-}Hsuan Yang and Mohammad Soleymani and Symeon Papadopoulos}, title = {The {NNI} Query-by-Example System for MediaEval 2015}, booktitle = {Working Notes Proceedings of the MediaEval 2015 Workshop, Wurzen, Germany, September 14-15, 2015}, series = {{CEUR} Workshop Proceedings}, volume = {1436}, publisher = {CEUR-WS.org}, year = {2015}, url = {https://ceur-ws.org/Vol-1436/Paper14.pdf}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mediaeval/HouPL0XLXFNXCZS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/HyLTDC15, author = {Nguyen Quy Hy and Siu Wa Lee and Xiaohai Tian and Minghui Dong and Engsiong Chng}, title = {High quality voice conversion using prosodic and high-resolution spectral features}, journal = {CoRR}, volume = {abs/1512.01809}, year = {2015}, url = {http://arxiv.org/abs/1512.01809}, eprinttype = {arXiv}, eprint = {1512.01809}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/HyLTDC15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ieicet/DoXCL14, author = {Van Hai Do and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Cross-Lingual Phone Mapping for Large Vocabulary Speech Recognition of Under-Resourced Languages}, journal = {{IEICE} Trans. Inf. Syst.}, volume = {97-D}, number = {2}, pages = {285--295}, year = {2014}, url = {https://doi.org/10.1587/transinf.E97.D.285}, doi = {10.1587/TRANSINF.E97.D.285}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ieicet/DoXCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/WuVCL14, author = {Zhizheng Wu and Tuomas Virtanen and Engsiong Chng and Haizhou Li}, title = {Exemplar-Based Sparse Representation With Residual Compensation for Voice Conversion}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {22}, number = {10}, pages = {1506--1521}, year = {2014}, url = {https://doi.org/10.1109/TASLP.2014.2333242}, doi = {10.1109/TASLP.2014.2333242}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/WuVCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/HuangXXXSL14, author = {Guangpu Huang and Chenglin Xu and Xiong Xiao and Lei Xie and Chng Eng Siong and Haizhou Li}, title = {Multi-view features in a {DNN-CRF} model for improved sentence unit detection on English broadcast news}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December 9-12, 2014}, pages = {1--9}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/APSIPA.2014.7041543}, doi = {10.1109/APSIPA.2014.7041543}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/HuangXXXSL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/WuGCL14, author = {Zhizheng Wu and Sheng Gao and Engsiong Chng and Haizhou Li}, title = {A study on replay attack and anti-spoofing for text-dependent speaker verification}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December 9-12, 2014}, pages = {1--5}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/APSIPA.2014.7041636}, doi = {10.1109/APSIPA.2014.7041636}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/WuGCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/XuPCL14, author = {Haihua Xu and Van Tung Pham and Engsiong Chng and Haizhou Li}, title = {Towards better keyword search performance on Malay broadcast news data}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2014, Chiang Mai, Thailand, December 9-12, 2014}, pages = {1--5}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/APSIPA.2014.7041580}, doi = {10.1109/APSIPA.2014.7041580}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/XuPCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/fusion/ZhongWNC14, author = {Xionghu Zhong and Wenwu Wang and Syed Mohsen Naqvi and Engsiong Chng}, title = {A Bayesian performance bound for time-delay of arrival based acoustic source tracking in a reverberant environment}, booktitle = {17th International Conference on Information Fusion, {FUSION} 2014, Salamanca, Spain, July 7-10, 2014}, pages = {1--8}, publisher = {{IEEE}}, year = {2014}, url = {https://ieeexplore.ieee.org/document/6916159/}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/fusion/ZhongWNC14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoLCL14, author = {Xiong Xiao and Jinyu Li and Engsiong Chng and Haizhou Li}, title = {Feature compensation using linear combination of speaker and environment dependent correction vectors}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {1720--1724}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6853892}, doi = {10.1109/ICASSP.2014.6853892}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XiaoLCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NguyenXCL14, author = {Duc Hoang Ha Nguyen and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Generalization of temporal filter and linear transformation for robust speech recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {1730--1734}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6853894}, doi = {10.1109/ICASSP.2014.6853894}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/NguyenXCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/DennisDLC14, author = {Jonathan William Dennis and Tran Huy Dat and Haizhou Li and Engsiong Chng}, title = {A discriminatively trained Hough Transform for frame-level phoneme recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {2514--2518}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6854053}, doi = {10.1109/ICASSP.2014.6854053}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/DennisDLC14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChongBCL14, author = {Tze Yuang Chong and Rafael E. Banchs and Engsiong Chng and Haizhou Li}, title = {Improving language modeling by using distance and co-occurrence information of word-pairs and its application to {LVCSR}}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {4883--4887}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6854530}, doi = {10.1109/ICASSP.2014.6854530}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/ChongBCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/PhamXCSLCL14, author = {Van Tung Pham and Haihua Xu and Nancy F. Chen and Sunil Sivadas and Boon Pang Lim and Engsiong Chng and Haizhou Li}, title = {Discriminative score normalization for keyword search decision}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {7078--7082}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6854973}, doi = {10.1109/ICASSP.2014.6854973}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/PhamXCSLCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DoXSL14, author = {Van Hai Do and Xiong Xiao and Chng Eng Siong and Haizhou Li}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Kernel density-based acoustic model with cross-lingual bottleneck features for resource limited {LVCSR}}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {6--10}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-2}, doi = {10.21437/INTERSPEECH.2014-2}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DoXSL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuSSL14, author = {Haihua Xu and Hang Su and Chng Eng Siong and Haizhou Li}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Semi-supervised training for bottle-neck feature based {DNN-HMM} hybrid systems}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2078--2082}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-472}, doi = {10.21437/INTERSPEECH.2014-472}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuSSL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuSL14, author = {Zhizheng Wu and Chng Eng Siong and Haizhou Li}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Joint nonnegative matrix factorization for exemplar-based voice conversion}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2509--2513}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-538}, doi = {10.21437/INTERSPEECH.2014-538}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuSL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DennisDS14, author = {Jonathan William Dennis and Tran Huy Dat and Chng Eng Siong}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Analysis of spectrogram image methods for sound event classification}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2533--2537}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-543}, doi = {10.21437/INTERSPEECH.2014-543}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DennisDS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuXHXCL14, author = {Chenglin Xu and Lei Xie and Guangpu Huang and Xiong Xiao and Engsiong Chng and Haizhou Li}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {A deep neural network approach for sentence boundary detection in broadcast news}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2887--2891}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-599}, doi = {10.21437/INTERSPEECH.2014-599}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuXHXCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/TianWLC14, author = {Xiaohai Tian and Zhizheng Wu and Siu Wa Lee and Engsiong Chng}, editor = {Minghui Dong and Jianhua Tao and Haizhou Li and Thomas Fang Zheng and Yanfeng Lu}, title = {Correlation-based frequency warping for voice conversion}, booktitle = {The 9th International Symposium on Chinese Spoken Language Processing, Singapore, September 12-14, 2014}, pages = {211--215}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ISCSLP.2014.6936725}, doi = {10.1109/ISCSLP.2014.6936725}, timestamp = {Mon, 18 Mar 2024 17:29:23 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/TianWLC14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/UedaWKXCL14, author = {Yuma Ueda and Longbiao Wang and Atsuhiko Kai and Xiong Xiao and Engsiong Chng and Haizhou Li}, editor = {Minghui Dong and Jianhua Tao and Haizhou Li and Thomas Fang Zheng and Yanfeng Lu}, title = {Single-channel dereverberation for distant-talking speech recognition by combining denoising autoencoder and temporal structure normalization}, booktitle = {The 9th International Symposium on Chinese Spoken Language Processing, Singapore, September 12-14, 2014}, pages = {379--383}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ISCSLP.2014.6936613}, doi = {10.1109/ISCSLP.2014.6936613}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/UedaWKXCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mediaeval/YangXXXLCYL0LMSL14, author = {Peng Yang and Haihua Xu and Xiong Xiao and Lei Xie and Cheung{-}Chi Leung and Hongjie Chen and Jia Yu and Hang Lv and Lei Wang and Su Jun Leow and Bin Ma and Chng Eng Siong and Haizhou Li}, editor = {Martha A. Larson and Bogdan Ionescu and Xavier Anguera and Maria Eskevich and Pavel Korshunov and Markus Schedl and Mohammad Soleymani and Georgios Petkos and Richard F. E. Sutcliffe and Jaeyoung Choi and Gareth J. F. Jones}, title = {The {NNI} Query-by-Example System for MediaEval 2014}, booktitle = {Working Notes Proceedings of the MediaEval 2014 Workshop, Barcelona, Catalunya, Spain, October 16-17, 2014}, series = {{CEUR} Workshop Proceedings}, volume = {1263}, publisher = {CEUR-WS.org}, year = {2014}, url = {https://ceur-ws.org/Vol-1263/mediaeval2014\_submission\_69.pdf}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mediaeval/YangXXXLCYL0LMSL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/PhamCSXCNCL14, author = {Van Tung Pham and Nancy F. Chen and Sunil Sivadas and Haihua Xu and I{-}Fan Chen and Chongjia Ni and Engsiong Chng and Haizhou Li}, title = {System and keyword dependent fusion for spoken term detection}, booktitle = {2014 {IEEE} Spoken Language Technology Workshop, {SLT} 2014, South Lake Tahoe, NV, USA, December 7-10, 2014}, pages = {430--435}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/SLT.2014.7078613}, doi = {10.1109/SLT.2014.7078613}, timestamp = {Sat, 31 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/PhamCSXCNCL14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/interspeech/2014, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014}, doi = {10.21437/INTERSPEECH.2014}, timestamp = {Thu, 22 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/2014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/prl/DennisTC13, author = {Jonathan William Dennis and Tran Huy Dat and Engsiong Chng}, title = {Overlapping sound event recognition using local spectrogram features and the generalised hough transform}, journal = {Pattern Recognit. Lett.}, volume = {34}, number = {9}, pages = {1085--1093}, year = {2013}, url = {https://doi.org/10.1016/j.patrec.2013.02.015}, doi = {10.1016/J.PATREC.2013.02.015}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/prl/DennisTC13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spe/TanTCLLDCXN13, author = {Yu Shyang Tan and Jiaqi Tan and Engsiong Chng and Bu{-}Sung Lee and Jiaming Li and Susumu Date and Hui Ping Chak and Xiong Xiao and Atsushi Narishige}, title = {Hadoop framework: impact of data organization on performance}, journal = {Softw. Pract. Exp.}, volume = {43}, number = {11}, pages = {1241--1260}, year = {2013}, url = {https://doi.org/10.1002/spe.1082}, doi = {10.1002/SPE.1082}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/spe/TanTCLLDCXN13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/DennisDC13, author = {Jonathan William Dennis and Tran Huy Dat and Engsiong Chng}, title = {Image Feature Representation of the Subband Power Distribution for Robust Sound Event Classification}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {21}, number = {2}, pages = {367--377}, year = {2013}, url = {https://doi.org/10.1109/TASL.2012.2226160}, doi = {10.1109/TASL.2012.2226160}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/DennisDC13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/acl/ChongBCL13, author = {Tze Yuang Chong and Rafael E. Banchs and Engsiong Chng and Haizhou Li}, title = {Modeling of term-distance and term-occurrence information for improving n-gram language model performance}, booktitle = {Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, {ACL} 2013, 4-9 August 2013, Sofia, Bulgaria, Volume 2: Short Papers}, pages = {233--237}, publisher = {The Association for Computer Linguistics}, year = {2013}, url = {https://aclanthology.org/P13-2042/}, timestamp = {Fri, 06 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/acl/ChongBCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/NgDDS13, author = {Wen Zheng Terence Ng and Tran Huy Dat and Jonathan William Dennis and Chng Eng Siong}, title = {A robust sound event recognition framework under {TV} playing conditions}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29 - November 1, 2013}, pages = {1--5}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/APSIPA.2013.6694265}, doi = {10.1109/APSIPA.2013.6694265}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/NgDDS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/NgDHS13, author = {Wen Zheng Terence Ng and Tran Huy Dat and Huynh Thai Hoa and Chng Eng Siong}, title = {Adaptive semi-supervised tree {SVM} for sound event recognition in home environments}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29 - November 1, 2013}, pages = {1--4}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/APSIPA.2013.6694194}, doi = {10.1109/APSIPA.2013.6694194}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/NgDHS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/NguyenMXCLL13, author = {Duc Hoang Ha Nguyen and Aleem Mushtaq and Xiong Xiao and Engsiong Chng and Haizhou Li and Chin{-}Hui Lee}, title = {A particle filter compensation approach to robust {LVCSR}}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29 - November 1, 2013}, pages = {1--7}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/APSIPA.2013.6694223}, doi = {10.1109/APSIPA.2013.6694223}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/apsipa/NguyenMXCLL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/TianWC13, author = {Xiaohai Tian and Zhizheng Wu and Engsiong Chng}, title = {Local partial least square regression for spectral mapping in voice conversion}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2013, Kaohsiung, Taiwan, October 29 - November 1, 2013}, pages = {1--6}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/APSIPA.2013.6694332}, doi = {10.1109/APSIPA.2013.6694332}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/TianWC13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/WuCL13, author = {Zhizheng Wu and Engsiong Chng and Haizhou Li}, title = {Conditional restricted Boltzmann machine for voice conversion}, booktitle = {2013 {IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013, Beijing, China, July 6-10, 2013}, pages = {104--108}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ChinaSIP.2013.6625307}, doi = {10.1109/CHINASIP.2013.6625307}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/chinasip/WuCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/LyuCL13, author = {Dau{-}Cheng Lyu and Engsiong Chng and Haizhou Li}, title = {Language diarization for conversational code-switch speech with pronunciation dictionary adaptation}, booktitle = {2013 {IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013, Beijing, China, July 6-10, 2013}, pages = {147--150}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ChinaSIP.2013.6625316}, doi = {10.1109/CHINASIP.2013.6625316}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/LyuCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/NgDDS13, author = {Wen Zheng Terence Ng and Tran Huy Dat and Jonathan William Dennis and Chng Eng Siong}, title = {Robust sound event recognition under {TV} playing conditions}, booktitle = {2013 {IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013, Beijing, China, July 6-10, 2013}, pages = {332--336}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ChinaSIP.2013.6625355}, doi = {10.1109/CHINASIP.2013.6625355}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/NgDDS13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/chinasip/XiaoCL13, author = {Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Constrained adaptation of histogram equalization for robust speech recognition}, booktitle = {2013 {IEEE} China Summit and International Conference on Signal and Information Processing, ChinaSIP 2013, Beijing, China, July 6-10, 2013}, pages = {360--364}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ChinaSIP.2013.6625361}, doi = {10.1109/CHINASIP.2013.6625361}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/chinasip/XiaoCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WuXCL13, author = {Zhizheng Wu and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Synthetic speech detection using temporal modulation feature}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013}, pages = {7234--7238}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICASSP.2013.6639067}, doi = {10.1109/ICASSP.2013.6639067}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/WuXCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LyuCL13, author = {Dau{-}Cheng Lyu and Engsiong Chng and Haizhou Li}, title = {Language diarization for code-switch conversational speech}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013}, pages = {7314--7318}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICASSP.2013.6639083}, doi = {10.1109/ICASSP.2013.6639083}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LyuCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoCL13, author = {Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Temporal filter design by minimum {KL} divergence criterion for robust speech recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013}, pages = {7908--7912}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICASSP.2013.6639204}, doi = {10.1109/ICASSP.2013.6639204}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XiaoCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DoXCL13, author = {Van Hai Do and Xiong Xiao and Engsiong Chng and Haizhou Li}, editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and Christophe Cerisara and C{\'{e}}cile Fougeron and Guillaume Gravier and Lori Lamel and Fran{\c{c}}ois Pellegrino and Pascal Perrier}, title = {Context-dependent phone mapping for {LVCSR} of under-resourced languages}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {500--504}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-143}, doi = {10.21437/INTERSPEECH.2013-143}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DoXCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XiaoCL13, author = {Xiong Xiao and Engsiong Chng and Haizhou Li}, editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and Christophe Cerisara and C{\'{e}}cile Fougeron and Guillaume Gravier and Lori Lamel and Fran{\c{c}}ois Pellegrino and Pascal Perrier}, title = {Attribute-based histogram equalization {(HEQ)} and its adaptation for robust speech recognition}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {876--880}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-259}, doi = {10.21437/INTERSPEECH.2013-259}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XiaoCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuLLCKL13, author = {Zhizheng Wu and Anthony Larcher and Kong{-}Aik Lee and Engsiong Chng and Tomi Kinnunen and Haizhou Li}, editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and Christophe Cerisara and C{\'{e}}cile Fougeron and Guillaume Gravier and Lori Lamel and Fran{\c{c}}ois Pellegrino and Pascal Perrier}, title = {Vulnerability evaluation of speaker verification under voice conversion spoofing: the effect of text constraints}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {950--954}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-293}, doi = {10.21437/INTERSPEECH.2013-293}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuLLCKL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuVKCL13, author = {Zhizheng Wu and Tuomas Virtanen and Tomi Kinnunen and Engsiong Chng and Haizhou Li}, editor = {Fr{\'{e}}d{\'{e}}ric Bimbot and Christophe Cerisara and C{\'{e}}cile Fougeron and Guillaume Gravier and Lori Lamel and Fran{\c{c}}ois Pellegrino and Pascal Perrier}, title = {Exemplar-based unit selection for voice conversion utilizing temporal information}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {3057--3061}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-667}, doi = {10.21437/INTERSPEECH.2013-667}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuVKCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ococosda/ChongXXTPLSL13, author = {Tze Yuang Chong and Xiong Xiao and Haihua Xu and Tien Ping Tan and Chau Khoa Pham and Dau{-}Cheng Lyu and Chng Eng Siong and Haizhou Li}, title = {The development and analysis of a Malay broadcasr news corpus}, booktitle = {2013 International Conference Oriental {COCOSDA} held jointly with 2013 Conference on Asian Spoken Language Research and Evaluation (O-COCOSDA/CASLRE), Gurgaon, India, November 25-27, 2013}, pages = {1--5}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICSDA.2013.6709862}, doi = {10.1109/ICSDA.2013.6709862}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ococosda/ChongXXTPLSL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ssw/WuVKCL13, author = {Zhizheng Wu and Tuomas Virtanen and Tomi Kinnunen and Eng Siong Chng and Haizhou Li}, title = {Exemplar-based voice conversion using non-negative spectrogram deconvolution}, booktitle = {The Eighth {ISCA} Tutorial and Research Workshop on Speech Synthesis, Barcelona, Spain, August 31-September 2, 2013}, pages = {201--206}, publisher = {{ISCA}}, year = {2013}, url = {http://www.isca-speech.org/archive/ssw8/ssw8\_201.html}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ssw/WuVKCL13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ieicet/WangXLMCL12, author = {Xiaoxuan Wang and Lei Xie and Mimi Lu and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Broadcast News Story Segmentation Using Conditional Random Fields and Multimodal Features}, journal = {{IEICE} Trans. Inf. Syst.}, volume = {95-D}, number = {5}, pages = {1206--1215}, year = {2012}, url = {https://doi.org/10.1587/transinf.E95.D.1206}, doi = {10.1587/TRANSINF.E95.D.1206}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ieicet/WangXLMCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/prl/DehzangiMCL12, author = {Omid Dehzangi and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Discriminative feature extraction for speech recognition using continuous output codes}, journal = {Pattern Recognit. Lett.}, volume = {33}, number = {13}, pages = {1703--1709}, year = {2012}, url = {https://doi.org/10.1016/j.patrec.2012.05.012}, doi = {10.1016/J.PATREC.2012.05.012}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/prl/DehzangiMCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spl/WuKCL12, author = {Zhizheng Wu and Tomi Kinnunen and Engsiong Chng and Haizhou Li}, title = {Mixture of Factor Analyzers Using Priors From Non-Parallel Speech for Voice Conversion}, journal = {{IEEE} Signal Process. Lett.}, volume = {19}, number = {12}, pages = {914--917}, year = {2012}, url = {https://doi.org/10.1109/LSP.2012.2225615}, doi = {10.1109/LSP.2012.2225615}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/spl/WuKCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/apsipa/WuKCLA12, author = {Zhizheng Wu and Tomi Kinnunen and Engsiong Chng and Haizhou Li and Eliathamby Ambikairajah}, title = {A study on spoofing attack in state-of-the-art speaker verification: the telephone speech case}, booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, {APSIPA} 2012, Hollywood, CA, USA, December 3-6, 2012}, pages = {1--5}, publisher = {{IEEE}}, year = {2012}, url = {https://ieeexplore.ieee.org/document/6411897/}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/apsipa/WuKCLA12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hytra/ChongBC12, author = {Tze Yuang Chong and Rafael E. Banchs and Eng Siong Chng}, editor = {Marta R. Costa{-}juss{\`{a}} and Patrik Lambert and Rafael E. Banchs and Reinhard Rapp and Bogdan Babych}, title = {An Empirical Evaluation of Stop Word Removal in Statistical Machine Translation}, booktitle = {Proceedings of the Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation {(ESIRMT)} and Hybrid Approaches to Machine Translation HyTra@EACL 2012, Avignon, France, April 23-27, 2012}, pages = {30--37}, publisher = {Association for Computational Linguistics}, year = {2012}, url = {https://aclanthology.org/W12-0104/}, timestamp = {Fri, 06 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hytra/ChongBC12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/DoXCL12, author = {Van Hai Do and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {A Phone Mapping Technique for Acoustic Modeling of Under-Resourced Languages}, booktitle = {2012 International Conference on Asian Language Processing, Hanoi, Vietnam, November 13-15, 2012}, pages = {233--236}, publisher = {{IEEE} Computer Society}, year = {2012}, url = {https://doi.org/10.1109/IALP.2012.17}, doi = {10.1109/IALP.2012.17}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ialp/DoXCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoLCL12, author = {Xiong Xiao and Jinyu Li and Engsiong Chng and Haizhou Li}, title = {Lasso environment model combination for robust speech recognition}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4305--4308}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6288871}, doi = {10.1109/ICASSP.2012.6288871}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XiaoLCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoCL12, author = {Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Joint spectral and temporal normalization of features for robust recognition of noisy and reverberated speech}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4325--4328}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6288876}, doi = {10.1109/ICASSP.2012.6288876}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XiaoCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KinnunenWLSCL12, author = {Tomi Kinnunen and Zhizheng Wu and Kong{-}Aik Lee and Filip Sedlak and Engsiong Chng and Haizhou Li}, title = {Vulnerability of speaker verification systems against voice conversion spoofing attacks: The case of telephone speech}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4401--4404}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6288895}, doi = {10.1109/ICASSP.2012.6288895}, timestamp = {Sat, 18 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/KinnunenWLSCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/VuLWTSBCSL12, author = {Ngoc Thang Vu and Dau{-}Cheng Lyu and Jochen Weiner and Dominic Telaar and Tim Schlippe and Fabian Blaicher and Engsiong Chng and Tanja Schultz and Haizhou Li}, title = {A first speech recognition system for Mandarin-English code-switch conversational speech}, booktitle = {2012 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2012, Kyoto, Japan, March 25-30, 2012}, pages = {4889--4892}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICASSP.2012.6289015}, doi = {10.1109/ICASSP.2012.6289015}, timestamp = {Sat, 31 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/VuLWTSBCSL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuSL12, author = {Zhizheng Wu and Chng Eng Siong and Haizhou Li}, title = {Detecting Converted Speech and Natural Speech for anti-Spoofing Attack in Speaker Recognition}, booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, September 9-13, 2012}, pages = {1700--1703}, publisher = {{ISCA}}, year = {2012}, url = {https://doi.org/10.21437/Interspeech.2012-465}, doi = {10.21437/INTERSPEECH.2012-465}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuSL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DennisDC12, author = {Jonathan William Dennis and Tran Huy Dat and Engsiong Chng}, title = {Overlapping Sound Event Recognition using Local Spectrogram Features with the Generalised Hough Transform}, booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, September 9-13, 2012}, pages = {2266--2269}, publisher = {{ISCA}}, year = {2012}, url = {https://doi.org/10.21437/Interspeech.2012-595}, doi = {10.21437/INTERSPEECH.2012-595}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DennisDC12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/DoXCL12, author = {Van Hai Do and Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Context dependant phone mapping for cross-lingual acoustic modeling}, booktitle = {8th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2012, Kowloon Tong, China, December 5-8, 2012}, pages = {16--20}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ISCSLP.2012.6423496}, doi = {10.1109/ISCSLP.2012.6423496}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/DoXCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/NguyenXCL12, author = {Duc Hoang Ha Nguyen and Xiong Xiao and Chng Eng Siong and Haizhou Li}, title = {An analysis of vector Taylor series model compensation for non-stationary noise in speech recognition}, booktitle = {8th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2012, Kowloon Tong, China, December 5-8, 2012}, pages = {131--135}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ISCSLP.2012.6423503}, doi = {10.1109/ISCSLP.2012.6423503}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/NguyenXCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sltu/WeinerVTMSLCL12, author = {Jochen Weiner and Ngoc Thang Vu and Dominic Telaar and Florian Metze and Tanja Schultz and Dau{-}Cheng Lyu and Engsiong Chng and Haizhou Li}, title = {Integration of language identification into a recognition system for spoken conversations containing code-Switches}, booktitle = {Third Workshop on Spoken Language Technologies for Under-resourced Languages, {SLTU} 2012, Cape Town, South Africa, May 7-9, 2012}, pages = {76--79}, publisher = {{ISCA}}, year = {2012}, url = {http://www.isca-speech.org/archive/sltu\_2012/weiner12\_sltu.html}, timestamp = {Tue, 29 Mar 2022 16:13:21 +0200}, biburl = {https://dblp.org/rec/conf/sltu/WeinerVTMSLCL12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ieicet/DehzangiMCL11, author = {Omid Dehzangi and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Error Corrective Fusion of Classifier Scores for Spoken Language Recognition}, journal = {{IEICE} Trans. Inf. Syst.}, volume = {94-D}, number = {12}, pages = {2503--2512}, year = {2011}, url = {https://doi.org/10.1587/transinf.E94.D.2503}, doi = {10.1587/TRANSINF.E94.D.2503}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ieicet/DehzangiMCL11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoLCL11, author = {Xiong Xiao and Jinyu Li and Engsiong Chng and Haizhou Li}, title = {Maximum likelihood adaptation of histogram equalization with constraint for robust speech recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2011, May 22-27, 2011, Prague Congress Center, Prague, Czech Republic}, pages = {5480--5483}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ICASSP.2011.5947599}, doi = {10.1109/ICASSP.2011.5947599}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XiaoLCL11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XiaoLSL11, author = {Xiong Xiao and Jinyu Li and Chng Eng Siong and Haizhou Li}, title = {Feature Normalization Using Structured Full Transforms for Robust Speech Recognition}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {693--696}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-206}, doi = {10.21437/INTERSPEECH.2011-206}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XiaoLSL11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TongMLS11, author = {Rong Tong and Bin Ma and Haizhou Li and Chng Eng Siong}, title = {Target-Aware Lattice Rescoring for Dialect Recognition}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {733--736}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-282}, doi = {10.21437/INTERSPEECH.2011-282}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/TongMLS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SamXBCLS11, author = {Sethserey Sam and Xiong Xiao and Laurent Besacier and Eric Castelli and Haizhou Li and Chng Eng Siong}, title = {Speech Modulation Features for Robust Nonnative Speech Accent Detection}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {2417--2420}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-629}, doi = {10.21437/INTERSPEECH.2011-629}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SamXBCLS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/MehtaPS11, author = {Kannu Mehta and Chau Khoa Pham and Chng Eng Siong}, title = {Linear Dynamic Models for Voice Activity Detection}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {2617--2620}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-669}, doi = {10.21437/INTERSPEECH.2011-669}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/MehtaPS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/prl/WangCL10, author = {Lei Wang and Engsiong Chng and Haizhou Li}, title = {A tree-construction search approach for multivariate time series motifs discovery}, journal = {Pattern Recognit. Lett.}, volume = {31}, number = {9}, pages = {869--875}, year = {2010}, url = {https://doi.org/10.1016/j.patrec.2010.01.005}, doi = {10.1016/J.PATREC.2010.01.005}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/prl/WangCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XiaoLCLL10, author = {Xiong Xiao and Jinyu Li and Engsiong Chng and Haizhou Li and Chin{-}Hui Lee}, title = {A Study on the Generalization Capability of Acoustic Models for Robust Speech Recognition}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {18}, number = {6}, pages = {1158--1169}, year = {2010}, url = {https://doi.org/10.1109/TASL.2009.2031236}, doi = {10.1109/TASL.2009.2031236}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/XiaoLCLL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/emnlp/ZhangZLC10, author = {Hui Zhang and Min Zhang and Haizhou Li and Engsiong Chng}, title = {Non-Isomorphic Forest Pair Translation}, booktitle = {Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, {EMNLP} 2010, 9-11 October 2010, {MIT} Stata Center, Massachusetts, USA, {A} meeting of SIGDAT, a Special Interest Group of the {ACL}}, pages = {440--450}, publisher = {{ACL}}, year = {2010}, url = {https://aclanthology.org/D10-1043/}, timestamp = {Tue, 28 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/emnlp/ZhangZLC10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/DehzangiMCL10, author = {Omid Dehzangi and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Error corrective classifier fusion for spoken Language Recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2010, 14-19 March 2010, Sheraton Dallas Hotel, Dallas, Texas, {USA}}, pages = {1994--1997}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ICASSP.2010.5495235}, doi = {10.1109/ICASSP.2010.5495235}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/DehzangiMCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpr/DehzangiMCL10, author = {Omid Dehzangi and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Framewise Phone Classification Using Weighted Fuzzy Classification Rules}, booktitle = {20th International Conference on Pattern Recognition, {ICPR} 2010, Istanbul, Turkey, 23-26 August 2010}, pages = {4186--4189}, publisher = {{IEEE} Computer Society}, year = {2010}, url = {https://doi.org/10.1109/ICPR.2010.1017}, doi = {10.1109/ICPR.2010.1017}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpr/DehzangiMCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TongMLC10, author = {Rong Tong and Bin Ma and Haizhou Li and Engsiong Chng}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Selecting phonotactic features for language recognition}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {737--740}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-273}, doi = {10.21437/INTERSPEECH.2010-273}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/TongMLC10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangXMCL10, author = {Xiaoxuan Wang and Lei Xie and Bin Ma and Engsiong Chng and Haizhou Li}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Phoneme lattice based texttiling towards multilingual story segmentation}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1305--1308}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-408}, doi = {10.21437/INTERSPEECH.2010-408}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangXMCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuKCL10, author = {Zhizheng Wu and Tomi Kinnunen and Engsiong Chng and Haizhou Li}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Text-independent {F0} transformation with non-parallel data for voice conversion}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1732--1735}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-497}, doi = {10.21437/INTERSPEECH.2010-497}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuKCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LyuTCL10, author = {Dau{-}Cheng Lyu and Tien Ping Tan and Engsiong Chng and Haizhou Li}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {{SEAME:} a Mandarin-English code-switching speech corpus in south-east asia}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1986--1989}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-563}, doi = {10.21437/INTERSPEECH.2010-563}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LyuTCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DehzangiMCL10, author = {Omid Dehzangi and Bin Ma and Engsiong Chng and Haizhou Li}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {A discriminative performance metric for {GMM-UBM} speaker identification}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {2114--2117}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-158}, doi = {10.21437/INTERSPEECH.2010-158}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DehzangiMCL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/TongMLS09, author = {Rong Tong and Bin Ma and Haizhou Li and Chng Eng Siong}, title = {A Target-Oriented Phonotactic Front-End for Spoken Language Recognition}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {17}, number = {7}, pages = {1335--1347}, year = {2009}, url = {https://doi.org/10.1109/TASL.2009.2016731}, doi = {10.1109/TASL.2009.2016731}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/TongMLS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/XiaoLCLL09, author = {Xiong Xiao and Jinyu Li and Engsiong Chng and Haizhou Li and Chin{-}Hui Lee}, title = {A study on hidden Markov model's generalization capability for speech recognition}, booktitle = {2009 {IEEE} Workshop on Automatic Speech Recognition {\&} Understanding, {ASRU} 2009, Merano/Meran, Italy, December 13-17, 2009}, pages = {255--260}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ASRU.2009.5373359}, doi = {10.1109/ASRU.2009.5373359}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/XiaoLCLL09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/NguyenLS09, author = {Trung Hieu Nguyen and Haizhou Li and Chng Eng Siong}, title = {Cluster criterion functions in spectral subspace and their application in speaker clustering}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan}, pages = {4085--4088}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICASSP.2009.4960526}, doi = {10.1109/ICASSP.2009.4960526}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/NguyenLS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiMLSZSYTKHPGLDNTEASSJ09, author = {Haizhou Li and Bin Ma and Kong{-}Aik Lee and Hanwu Sun and Donglai Zhu and Khe Chai Sim and Changhuai You and Rong Tong and Ismo K{\"{a}}rkk{\"{a}}inen and Chien{-}Lin Huang and Vladimir Pervouchine and Wu Guo and Yijie Li and Li{-}Rong Dai and Mohaddeseh Nosratighods and Tharmarajah Thiruvaran and Julien Epps and Eliathamby Ambikairajah and Chng Eng Siong and Tanja Schultz and Qin Jin}, title = {The {I4U} system in {NIST} 2008 speaker recognition evaluation}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan}, pages = {4201--4204}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICASSP.2009.4960555}, doi = {10.1109/ICASSP.2009.4960555}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiMLSZSYTKHPGLDNTEASSJ09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LongMLGSD09, author = {Yanhua Long and Bin Ma and Haizhou Li and Wu Guo and Chng Eng Siong and Li{-}Rong Dai}, title = {Exploiting prosodic information for Speaker Recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan}, pages = {4225--4228}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICASSP.2009.4960561}, doi = {10.1109/ICASSP.2009.4960561}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LongMLGSD09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmcs/WangSL09, author = {Lei Wang and Chng Eng Siong and Haizhou Li}, title = {Efficient sparse self-similarity matrix construction for repeating sequence detection}, booktitle = {Proceedings of the 2009 {IEEE} International Conference on Multimedia and Expo, {ICME} 2009, June 28 - July 2, 2009, New York City, NY, {USA}}, pages = {458--461}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ICME.2009.5202533}, doi = {10.1109/ICME.2009.5202533}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icmcs/WangSL09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TongMLCL09, author = {Rong Tong and Bin Ma and Haizhou Li and Engsiong Chng and Kong{-}Aik Lee}, title = {Target-aware language models for spoken language recognition}, booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009}, pages = {200--203}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-75}, doi = {10.21437/INTERSPEECH.2009-75}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/TongMLCL09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DehzangiMCL09, author = {Omid Dehzangi and Bin Ma and Engsiong Chng and Haizhou Li}, title = {Discriminative feature transformation using output coding for speech recognition}, booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009}, pages = {2979--2982}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-754}, doi = {10.21437/INTERSPEECH.2009-754}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DehzangiMCL09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ism/YounessianRS09, author = {Ehsan Younessian and Deepu Rajan and Chng Eng Siong}, title = {Improved Keypoint Matching Method for Near-Duplicate Keyframe Retrieval}, booktitle = {11th {IEEE} International Symposium on Multimedia, {ISM} 2009, San Diego, California, USA, December 14-16, 2009}, pages = {298--303}, publisher = {{IEEE} Computer Society}, year = {2009}, url = {https://doi.org/10.1109/ISM.2009.19}, doi = {10.1109/ISM.2009.19}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ism/YounessianRS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/asc/CheokZC08, author = {Adrian David Cheok and Jian Zhang and Chng Eng Siong}, title = {Efficient mobile phone Chinese optical character recognition systems by use of heuristic fuzzy rules and bigram Markov language models}, journal = {Appl. Soft Comput.}, volume = {8}, number = {2}, pages = {1005--1017}, year = {2008}, url = {https://doi.org/10.1016/j.asoc.2007.02.013}, doi = {10.1016/J.ASOC.2007.02.013}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/asc/CheokZC08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/mms/WangXCLT08, author = {Jinjun Wang and Changsheng Xu and Engsiong Chng and Hanqing Lu and Qi Tian}, title = {Automatic composition of broadcast sports video}, journal = {Multim. Syst.}, volume = {14}, number = {4}, pages = {179--193}, year = {2008}, url = {https://doi.org/10.1007/s00530-008-0112-6}, doi = {10.1007/S00530-008-0112-6}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/mms/WangXCLT08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XiaoSL08, author = {Xiong Xiao and Chng Eng Siong and Haizhou Li}, title = {Normalization of the Speech Modulation Spectra for Robust Speech Recognition}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {16}, number = {8}, pages = {1662--1674}, year = {2008}, url = {https://doi.org/10.1109/TASL.2008.2002082}, doi = {10.1109/TASL.2008.2002082}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/XiaoSL08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/csse/TanTCG08, author = {Choon{-}Ching Tan and Su{-}Lim Tan and Chng Eng Siong and Wooi{-}Boon Goh}, title = {{MICRO-EBLOCK:} {A} Modular Platform for Embedded System Education}, booktitle = {International Conference on Computer Science and Software Engineering, {CSSE} 2008, Volume 5: E-learning and Knowledge Management / Socially Informed and Instructinal Design / Learning Systems Platforms and Architectures / Modeling and Representation / Other Applications , December 12-14, 2008, Wuhan, China}, pages = {299--303}, publisher = {{IEEE} Computer Society}, year = {2008}, url = {https://doi.org/10.1109/CSSE.2008.1322}, doi = {10.1109/CSSE.2008.1322}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/csse/TanTCG08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TongMLC08, author = {Rong Tong and Bin Ma and Haizhou Li and Engsiong Chng}, title = {Target-oriented phone tokenizers for spoken language recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2008, March 30 - April 4, 2008, Caesars Palace, Las Vegas, Nevada, {USA}}, pages = {4221--4224}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/ICASSP.2008.4518586}, doi = {10.1109/ICASSP.2008.4518586}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/TongMLC08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpr/DehzangiMCL08, author = {Omid Dehzangi and Bin Ma and Chng Eng Siong and Haizhou Li}, title = {Fuzzy rule selection using Iterative Rule Learning for speech data classification}, booktitle = {19th International Conference on Pattern Recognition {(ICPR} 2008), December 8-11, 2008, Tampa, Florida, {USA}}, pages = {1--4}, publisher = {{IEEE} Computer Society}, year = {2008}, url = {https://doi.org/10.1109/ICPR.2008.4761266}, doi = {10.1109/ICPR.2008.4761266}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpr/DehzangiMCL08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/NguyenCL08, author = {Trung Hieu Nguyen and Engsiong Chng and Haizhou Li}, title = {T-test distance and clustering criterion for speaker diarization}, booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, September 22-26, 2008}, pages = {36--39}, publisher = {{ISCA}}, year = {2008}, url = {https://doi.org/10.21437/Interspeech.2008-7}, doi = {10.21437/INTERSPEECH.2008-7}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/NguyenCL08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/TongMLC08, author = {Rong Tong and Bin Ma and Haizhou Li and Engsiong Chng}, title = {Target-oriented phone selection from universal phone set for spoken language recognition}, booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, September 22-26, 2008}, pages = {715--718}, publisher = {{ISCA}}, year = {2008}, url = {https://doi.org/10.21437/Interspeech.2008-224}, doi = {10.21437/INTERSPEECH.2008-224}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/TongMLC08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/XiaoSL08, author = {Xiong Xiao and Chng Eng Siong and Haizhou Li}, editor = {Helen M. Meng and Hui Jiang and Jianhua Tao and Ren{-}Hua Wang}, title = {Effect of Feature Smoothing for Robust Speech Recognition}, booktitle = {6th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2008, 16-19 December, 2008, Kunming, China}, pages = {73--76}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/CHINSL.2008.ECP.30}, doi = {10.1109/CHINSL.2008.ECP.30}, timestamp = {Mon, 18 Mar 2024 17:29:23 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/XiaoSL08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/DehzangiMSL08, author = {Omid Dehzangi and Bin Ma and Chng Eng Siong and Haizhou Li}, editor = {Helen M. Meng and Hui Jiang and Jianhua Tao and Ren{-}Hua Wang}, title = {Discriminative Output Coding Features for Speech Recognition}, booktitle = {6th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2008, 16-19 December, 2008, Kunming, China}, pages = {89--92}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/CHINSL.2008.ECP.34}, doi = {10.1109/CHINSL.2008.ECP.34}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/DehzangiMSL08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spl/XiaoSL07, author = {Xiong Xiao and Chng Eng Siong and Haizhou Li}, title = {Temporal Structure Normalization of Speech Feature for Robust Speech Recognition}, journal = {{IEEE} Signal Process. Lett.}, volume = {14}, number = {7}, pages = {500--503}, year = {2007}, url = {https://doi.org/10.1109/LSP.2006.891341}, doi = {10.1109/LSP.2006.891341}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/spl/XiaoSL07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tmm/WangCXLT07, author = {Jinjun Wang and Engsiong Chng and Changsheng Xu and Hanqing Lu and Qi Tian}, title = {Generation of Personalized Music Sports Video Using Multimodal Cues}, journal = {{IEEE} Trans. Multim.}, volume = {9}, number = {3}, pages = {576--588}, year = {2007}, url = {https://doi.org/10.1109/TMM.2006.888013}, doi = {10.1109/TMM.2006.888013}, timestamp = {Thu, 01 Oct 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tmm/WangCXLT07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/clear/KohSNNMCLR07, author = {Chin{-}Wei Eugene Koh and Hanwu Sun and Tin Lay Nwe and Trung Hieu Nguyen and Bin Ma and Chng Eng Siong and Haizhou Li and Susanto Rahardja}, editor = {Rainer Stiefelhagen and Rachel Bowers and Jonathan G. Fiscus}, title = {Speaker Diarization Using Direction of Arrival Estimate and Acoustic Feature Information: The {I2R-NTU} Submission for the {NIST} {RT} 2007 Evaluation}, booktitle = {Multimodal Technologies for Perception of Humans, International Evaluation Workshops {CLEAR} 2007 and {RT} 2007, Baltimore, MD, USA, May 8-11, 2007, Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {4625}, pages = {484--496}, publisher = {Springer}, year = {2007}, url = {https://doi.org/10.1007/978-3-540-68585-2\_45}, doi = {10.1007/978-3-540-68585-2\_45}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/clear/KohSNNMCLR07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TongLMCC07, author = {Rong Tong and Haizhou Li and Bin Ma and Engsiong Chng and Siu{-}Yeung Cho}, title = {Spoken Language Recognition with Relevance Feedback}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April 15-20, 2007}, pages = {861--864}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ICASSP.2007.367206}, doi = {10.1109/ICASSP.2007.367206}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/TongLMCC07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XiaoCL07, author = {Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Normalizing the Speech Modulation Spectrum for Robust Speech Recognition}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April 15-20, 2007}, pages = {1021--1024}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ICASSP.2007.367246}, doi = {10.1109/ICASSP.2007.367246}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XiaoCL07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmcs/WangLC07, author = {Lei Wang and Haizhou Li and Engsiong Chng}, title = {A Vector-Based Approach to Broadcast Audio Database Indexing and Retrieval}, booktitle = {Proceedings of the 2007 {IEEE} International Conference on Multimedia and Expo, {ICME} 2007, July 2-5, 2007, Beijing, China}, pages = {512--515}, publisher = {{IEEE} Computer Society}, year = {2007}, url = {https://doi.org/10.1109/ICME.2007.4284699}, doi = {10.1109/ICME.2007.4284699}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icmcs/WangLC07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpads/BaiCB07, author = {Yunfei Bai and Chng Eng Siong and Gorthi Prashant Bhanu}, title = {An {MCU} description methodology for initialization code generation software}, booktitle = {13th International Conference on Parallel and Distributed Systems, {ICPADS} 2007, Hsinchu, Taiwan, December 5-7, 2007}, pages = {1--7}, publisher = {{IEEE} Computer Society}, year = {2007}, url = {https://doi.org/10.1109/ICPADS.2007.4447796}, doi = {10.1109/ICPADS.2007.4447796}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpads/BaiCB07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XiaoCL07, author = {Xiong Xiao and Engsiong Chng and Haizhou Li}, title = {Evaluating the temporal structure normalisation technique on the Aurora-4 task}, booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007}, pages = {1070--1073}, publisher = {{ISCA}}, year = {2007}, url = {https://doi.org/10.21437/Interspeech.2007-106}, doi = {10.21437/INTERSPEECH.2007-106}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XiaoCL07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/KohSNNMCLR07, author = {Chin{-}Wei Eugene Koh and Hanwu Sun and Tin Lay Nwe and Trung Hieu Nguyen and Bin Ma and Engsiong Chng and Haizhou Li and Susanto Rahardja}, title = {Using direction of arrival estimate and acoustic feature information in speaker diarization}, booktitle = {{INTERSPEECH} 2007, 8th Annual Conference of the International Speech Communication Association, Antwerp, Belgium, August 27-31, 2007}, pages = {2149--2152}, publisher = {{ISCA}}, year = {2007}, url = {https://doi.org/10.21437/Interspeech.2007-580}, doi = {10.21437/INTERSPEECH.2007-580}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/KohSNNMCLR07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TongMZLC06, author = {Rong Tong and Bin Ma and Donglai Zhu and Haizhou Li and Engsiong Chng}, title = {Integrating Acoustic, Prosodic and Phonotactic Features for Spoken Language Identification}, booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006}, pages = {205--208}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/ICASSP.2006.1659993}, doi = {10.1109/ICASSP.2006.1659993}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/TongMZLC06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmcs/WangCXLT06, author = {Jinjun Wang and Engsiong Chng and Changsheng Xu and Hanqing Lu and Xiaofeng Tong}, title = {Identify Sports Video Shots with "Happy" or "Sad" Emotions}, booktitle = {Proceedings of the 2006 {IEEE} International Conference on Multimedia and Expo, {ICME} 2006, July 9-12 2006, Toronto, Ontario, Canada}, pages = {877--880}, publisher = {{IEEE} Computer Society}, year = {2006}, url = {https://doi.org/10.1109/ICME.2006.262641}, doi = {10.1109/ICME.2006.262641}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icmcs/WangCXLT06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmcs/WangCX06, author = {Jinjun Wang and Engsiong Chng and Changsheng Xu}, title = {Fully and Semi-Automatic Music Sports Video Composition}, booktitle = {Proceedings of the 2006 {IEEE} International Conference on Multimedia and Expo, {ICME} 2006, July 9-12 2006, Toronto, Ontario, Canada}, pages = {1897--1900}, publisher = {{IEEE} Computer Society}, year = {2006}, url = {https://doi.org/10.1109/ICME.2006.262926}, doi = {10.1109/ICME.2006.262926}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icmcs/WangCX06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpr/WangXC06, author = {Jinjun Wang and Changsheng Xu and Engsiong Chng}, title = {Automatic Sports Video Genre Classification using Pseudo-2D-HMM}, booktitle = {18th International Conference on Pattern Recognition {(ICPR} 2006), 20-24 August 2006, Hong Kong, China}, pages = {778--781}, publisher = {{IEEE} Computer Society}, year = {2006}, url = {https://doi.org/10.1109/ICPR.2006.308}, doi = {10.1109/ICPR.2006.308}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpr/WangXC06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/XiaoLC06, author = {Xiong Xiao and Haizhou Li and Engsiong Chng}, editor = {Qiang Huo and Bin Ma and Chng Eng Siong and Haizhou Li}, title = {Vector Autoregressive Model for Missing Feature Reconstruction}, booktitle = {Chinese Spoken Language Processing, 5th International Symposium, {ISCSLP} 2006, Singapore, December 13-16, 2006, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {4274}, pages = {315--324}, publisher = {Springer}, year = {2006}, url = {https://doi.org/10.1007/11939993\_35}, doi = {10.1007/11939993\_35}, timestamp = {Mon, 13 Mar 2023 16:58:28 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/XiaoLC06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/LeeSTMDYZKWKEL06, author = {Kong{-}Aik Lee and Hanwu Sun and Rong Tong and Bin Ma and Minghui Dong and Changhuai You and Donglai Zhu and Chin{-}Wei Eugene Koh and Lei Wang and Tomi Kinnunen and Chng Eng Siong and Haizhou Li}, editor = {Qiang Huo and Bin Ma and Chng Eng Siong and Haizhou Li}, title = {The {IIR} Submission to {CSLP} 2006 Speaker Recognition Evaluation}, booktitle = {Chinese Spoken Language Processing, 5th International Symposium, {ISCSLP} 2006, Singapore, December 13-16, 2006, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {4274}, pages = {494--505}, publisher = {Springer}, year = {2006}, url = {https://doi.org/10.1007/11939993\_52}, doi = {10.1007/11939993\_52}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/LeeSTMDYZKWKEL06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/TongMLYZKSDCL06, author = {Rong Tong and Bin Ma and Kong{-}Aik Lee and Changhuai You and Donglai Zhu and Tomi Kinnunen and Hanwu Sun and Minghui Dong and Chng Eng Siong and Haizhou Li}, editor = {Qiang Huo and Bin Ma and Chng Eng Siong and Haizhou Li}, title = {Fusion of Acoustic and Tokenization Features for Speaker Recognition}, booktitle = {Chinese Spoken Language Processing, 5th International Symposium, {ISCSLP} 2006, Singapore, December 13-16, 2006, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {4274}, pages = {566--577}, publisher = {Springer}, year = {2006}, url = {https://doi.org/10.1007/11939993\_59}, doi = {10.1007/11939993\_59}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/TongMLYZKSDCL06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/iscslp/2006, editor = {Qiang Huo and Bin Ma and Chng Eng Siong and Haizhou Li}, title = {Chinese Spoken Language Processing, 5th International Symposium, {ISCSLP} 2006, Singapore, December 13-16, 2006, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {4274}, publisher = {Springer}, year = {2006}, url = {https://doi.org/10.1007/11939993}, doi = {10.1007/11939993}, isbn = {3-540-49665-3}, timestamp = {Mon, 13 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/2006.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijautcomp/ChngC05, author = {Eng Siong Chng and Sheng Chen}, title = {Determining the optimal decision delay parameter for a linear equalizer}, journal = {Int. J. Autom. Comput.}, volume = {2}, number = {1}, pages = {20--24}, year = {2005}, url = {https://doi.org/10.1007/s11633-005-0020-6}, doi = {10.1007/S11633-005-0020-6}, timestamp = {Fri, 21 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijautcomp/ChngC05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangCX05, author = {Jinjun Wang and Engsiong Chng and Changsheng Xu}, title = {Soccer replay detection using scene transition structure analysis}, booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23, 2005}, pages = {433--436}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/ICASSP.2005.1415434}, doi = {10.1109/ICASSP.2005.1415434}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangCX05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmcs/YuHYC05, author = {Xinguo Yu and Tze Sen Hay and Xin Yan and Engsiong Chng}, title = {A Player-Possession Acquisition System for Broadcast Soccer Video}, booktitle = {Proceedings of the 2005 {IEEE} International Conference on Multimedia and Expo, {ICME} 2005, July 6-9, 2005, Amsterdam, The Netherlands}, pages = {522--525}, publisher = {{IEEE} Computer Society}, year = {2005}, url = {https://doi.org/10.1109/ICME.2005.1521475}, doi = {10.1109/ICME.2005.1521475}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icmcs/YuHYC05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mm/WangXSDWT05, author = {Jinjun Wang and Changsheng Xu and Chng Eng Siong and Ling{-}Yu Duan and Kongwah Wan and Qi Tian}, editor = {HongJiang Zhang and Tat{-}Seng Chua and Ralf Steinmetz and Mohan S. Kankanhalli and Lynn Wilcox}, title = {Automatic generation of personalized music sports video}, booktitle = {Proceedings of the 13th {ACM} International Conference on Multimedia, Singapore, November 6-11, 2005}, pages = {735--744}, publisher = {{ACM}}, year = {2005}, url = {https://doi.org/10.1145/1101149.1101309}, doi = {10.1145/1101149.1101309}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/mm/WangXSDWT05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icc/ChenC04, author = {Sheng Chen and Engsiong Chng}, title = {Concurrent constant modulus algorithm and soft decision directed scheme for fractionally-spaced blind equalization}, booktitle = {Proceedings of {IEEE} International Conference on Communications, {ICC} 2004, Paris, France, 20-24 June 2004}, pages = {2342--2346}, publisher = {{IEEE}}, year = {2004}, url = {https://doi.org/10.1109/ICC.2004.1312937}, doi = {10.1109/ICC.2004.1312937}, timestamp = {Tue, 04 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icc/ChenC04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icip/WangXSYT04, author = {Jinjun Wang and Changsheng Xu and Chng Eng Siong and Xinguo Yu and Qi Tian}, title = {Event detection based on non-broadcast sports video}, booktitle = {Proceedings of the 2004 International Conference on Image Processing, {ICIP} 2004, Singapore, October 24-27, 2004}, pages = {1637--1640}, publisher = {{IEEE}}, year = {2004}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icip/WangXSYT04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icmcs/WangT04, author = {Jinjun Wang and Changsheng Xu and Chng Eng Siong and Qi Tian}, title = {Sports highlight detection from keyword sequences using {HMM}}, booktitle = {Proceedings of the 2004 {IEEE} International Conference on Multimedia and Expo, {ICME} 2004, 27-30 June 2004, Taipei, Taiwan}, pages = {599--602}, publisher = {{IEEE} Computer Society}, year = {2004}, timestamp = {Wed, 16 Oct 2019 14:14:56 +0200}, biburl = {https://dblp.org/rec/conf/icmcs/WangT04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icpr/XuGSRTW04, author = {Wenjie Xu and Cuntai Guan and Chng Eng Siong and S. Ranganatha and M. Thulasidas and Jiankang Wu}, title = {High Accuracy Classification of {EEG} Signal}, booktitle = {17th International Conference on Pattern Recognition, {ICPR} 2004, Cambridge, UK, August 23-26, 2004}, pages = {391--394}, publisher = {{IEEE} Computer Society}, year = {2004}, url = {https://doi.org/10.1109/ICPR.2004.1334229}, doi = {10.1109/ICPR.2004.1334229}, timestamp = {Fri, 24 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icpr/XuGSRTW04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/mm/WangXSWT04, author = {Jinjun Wang and Changsheng Xu and Chng Eng Siong and Kongwah Wan and Qi Tian}, editor = {Henning Schulzrinne and Nevenka Dimitrova and Martina Angela Sasse and Sue B. Moon and Rainer Lienhart}, title = {Automatic replay generation for soccer video broadcasting}, booktitle = {Proceedings of the 12th {ACM} International Conference on Multimedia, New York, NY, USA, October 10-16, 2004}, pages = {32--39}, publisher = {{ACM}}, year = {2004}, url = {https://doi.org/10.1145/1027527.1027535}, doi = {10.1145/1027527.1027535}, timestamp = {Tue, 06 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/mm/WangXSWT04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/spl/ChngYB96, author = {Eng Siong Chng and Howard Hua Yang and Siegfried B{\"{o}}s}, title = {Orthogonal least-squares learning algorithm with local adaptation process for the radial basis function networks}, journal = {{IEEE} Signal Process. Lett.}, volume = {3}, number = {8}, pages = {253--255}, year = {1996}, url = {https://doi.org/10.1109/97.511811}, doi = {10.1109/97.511811}, timestamp = {Fri, 09 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/spl/ChngYB96.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tnn/ChngCM96, author = {Engsiong Chng and Sheng Chen and Bernard Mulgrew}, title = {Gradient radial basis function networks for nonlinear and nonstationary time series prediction}, journal = {{IEEE} Trans. Neural Networks}, volume = {7}, number = {1}, pages = {190--194}, year = {1996}, url = {https://doi.org/10.1109/72.478403}, doi = {10.1109/72.478403}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tnn/ChngCM96.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icnn/BosC96, author = {Siegfried B{\"{o}}s and Eng Siong Chng}, title = {Using weight decay to optimize the generalization ability of a perceptron}, booktitle = {Proceedings of International Conference on Neural Networks (ICNN'96), Washington, DC, USA, June 3-6, 1996}, pages = {241--246}, publisher = {{IEEE}}, year = {1996}, url = {https://doi.org/10.1109/ICNN.1996.548898}, doi = {10.1109/ICNN.1996.548898}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icnn/BosC96.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tsp/ChngCM95, author = {Engsiong Chng and Sheng Chen and Bernard Mulgrew}, title = {Efficient computational schemes for the orthogonal least squares algorithm}, journal = {{IEEE} Trans. Signal Process.}, volume = {43}, number = {1}, pages = {373--376}, year = {1995}, url = {https://doi.org/10.1109/78.365331}, doi = {10.1109/78.365331}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tsp/ChngCM95.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/Chng0M94, author = {Engsiong Chng and Sheng Chen and Bernard Mulgrew}, title = {Reducing the computational requirement of the orthogonal least squares algorithm}, booktitle = {Proceedings of {ICASSP} '94: {IEEE} International Conference on Acoustics, Speech and Signal Processing, Adelaide, South Australia, Australia, April 19-22, 1994}, pages = {529--532}, publisher = {{IEEE} Computer Society}, year = {1994}, url = {https://doi.org/10.1109/ICASSP.1994.389973}, doi = {10.1109/ICASSP.1994.389973}, timestamp = {Thu, 23 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/Chng0M94.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.