Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Sheng Li 0010
@article{DBLP:journals/corr/abs-2401-13249,
author = {Wangjin Zhou and
Zhengdong Yang and
Chenhui Chu and
Sheng Li and
Raj Dabre and
Yi Zhao and
Tatsuya Kawahara},
title = {{MOS-FAD:} Improving Fake Audio Detection Via Automatic Mean Opinion
Score Prediction},
journal = {CoRR},
volume = {abs/2401.13249},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2401.13249},
doi = {10.48550/ARXIV.2401.13249},
eprinttype = {arXiv},
eprint = {2401.13249},
timestamp = {Tue, 26 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2401-13249.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jclc/KakLCK23,
author = {Soky Kak and
Sheng Li and
Chenhui Chu and
Tatsuya Kawahara},
title = {Finetuning Pretrained Model with Embedding of Domain and Language
Information for {ASR} of Very Low-Resource Settings},
journal = {Int. J. Asian Lang. Process.},
volume = {33},
number = {4},
pages = {2350024:1--2350024:17},
year = {2023},
url = {https://doi.org/10.1142/S2717554523500248},
doi = {10.1142/S2717554523500248},
timestamp = {Mon, 01 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jclc/KakLCK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/LinDWLD23,
author = {Yuqin Lin and
Jianwu Dang and
Longbiao Wang and
Sheng Li and
Chenchen Ding},
title = {Disordered speech recognition considering low resources and abnormal
articulation},
journal = {Speech Commun.},
volume = {155},
pages = {103002},
year = {2023},
url = {https://doi.org/10.1016/j.specom.2023.103002},
doi = {10.1016/J.SPECOM.2023.103002},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/LinDWLD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/ShimizuC0K23,
author = {Shuichiro Shimizu and
Chenhui Chu and
Sheng Li and
Sadao Kurohashi},
editor = {Anna Rogers and
Jordan L. Boyd{-}Graber and
Naoaki Okazaki},
title = {Towards Speech Dialogue Translation Mediating Speakers of Different
Languages},
booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023,
Toronto, Canada, July 9-14, 2023},
pages = {1122--1134},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.findings-acl.72},
doi = {10.18653/V1/2023.FINDINGS-ACL.72},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/ShimizuC0K23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/acl/YangLLS23,
author = {Longfei Yang and
Jiyi Li and
Sheng Li and
Takahiro Shinozaki},
editor = {Anna Rogers and
Jordan L. Boyd{-}Graber and
Naoaki Okazaki},
title = {Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot
Attention},
booktitle = {Findings of the Association for Computational Linguistics: {ACL} 2023,
Toronto, Canada, July 9-14, 2023},
pages = {4928--4938},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.findings-acl.304},
doi = {10.18653/V1/2023.FINDINGS-ACL.304},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/acl/YangLLS23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/QiHZLWLX23,
author = {Zili Qi and
Xinhui Hu and
Wangjin Zhou and
Sheng Li and
Hao Wu and
Jian Lu and
Xinkang Xu},
title = {{LE-SSL-MOS:} Self-Supervised Learning {MOS} Prediction with Listener
Enhancement},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2023, Taipei, Taiwan, December 16-20, 2023},
pages = {1--6},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ASRU57964.2023.10389788},
doi = {10.1109/ASRU57964.2023.10389788},
timestamp = {Fri, 22 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/asru/QiHZLWLX23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/WeiYGLCOL23,
author = {Wenqing Wei and
Zhengdong Yang and
Yuan Gao and
Jiyi Li and
Chenhui Chu and
Shogo Okada and
Sheng Li},
title = {FedCPC: An Effective Federated Contrastive Learning Method for Privacy
Preserving Early-Stage Alzheimers Speech Detection},
booktitle = {{IEEE} Automatic Speech Recognition and Understanding Workshop, {ASRU}
2023, Taipei, Taiwan, December 16-20, 2023},
pages = {1--6},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ASRU57964.2023.10389690},
doi = {10.1109/ASRU57964.2023.10389690},
timestamp = {Fri, 22 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/asru/WeiYGLCOL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icann/LiL23,
author = {Sheng Li and
Jiyi Li},
editor = {Lazaros Iliadis and
Antonios Papaleonidas and
Plamen P. Angelov and
Chrisina Jayne},
title = {Correction while Recognition: Combining Pretrained Language Model
for Taiwan-Accented Speech Recognition},
booktitle = {Artificial Neural Networks and Machine Learning - {ICANN} 2023 - 32nd
International Conference on Artificial Neural Networks, Heraklion,
Crete, Greece, September 26-29, 2023, Proceedings, Part {VII}},
series = {Lecture Notes in Computer Science},
volume = {14260},
pages = {389--400},
publisher = {Springer},
year = {2023},
url = {https://doi.org/10.1007/978-3-031-44195-0\_32},
doi = {10.1007/978-3-031-44195-0\_32},
timestamp = {Sat, 14 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icann/LiL23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KakLCK23,
author = {Soky Kak and
Sheng Li and
Chenhui Chu and
Tatsuya Kawahara},
title = {Domain and Language Adaptation Using Heterogeneous Datasets for Wav2vec2.0-Based
Speech Recognition of Low-Resource Language},
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/ICASSP49357.2023.10095644},
doi = {10.1109/ICASSP49357.2023.10095644},
timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KakLCK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/KorvingLZSMB23,
author = {Helen Korving and
Sheng Li and
Di Zhou and
Paula Sophia Sterkenburg and
Panos Markopoulos and
Emilia I. Barakova},
title = {Development of a Pain Signaling System Using Machine Learning},
booktitle = {{IEEE} International Conference on Acoustics, Speech, and Signal Processing,
{ICASSP} 2023 - Workshops, Rhodes Island, Greece, June 4-10, 2023},
pages = {1--5},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/ICASSPW59220.2023.10193643},
doi = {10.1109/ICASSPW59220.2023.10193643},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/KorvingLZSMB23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiuGYYLDMHCCK23,
author = {Qianying Liu and
Zhuo Gong and
Zhengdong Yang and
Yuhang Yang and
Sheng Li and
Chenchen Ding and
Nobuaki Minematsu and
Hao Huang and
Fei Cheng and
Chenhui Chu and
Sadao Kurohashi},
title = {Hierarchical Softmax for End-To-End Low-Resource Multilingual 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/ICASSP49357.2023.10095133},
doi = {10.1109/ICASSP49357.2023.10095133},
timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiuGYYLDMHCCK23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TanCLY23,
author = {Chao Tan and
Yang Cao and
Sheng Li and
Masatoshi Yoshikawa},
title = {General or Specific? Investigating Effective Privacy Protection in
Federated Learning for Speech Emotion 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/ICASSP49357.2023.10096844},
doi = {10.1109/ICASSP49357.2023.10096844},
timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TanCLY23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangYHHL23,
author = {Kai Wang and
Yuhang Yang and
Hao Huang and
Ying Hu and
Sheng Li},
title = {Speakeraugment: Data Augmentation for Generalizable Source Separation
via Speaker Parameter Manipulation},
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/ICASSP49357.2023.10094767},
doi = {10.1109/ICASSP49357.2023.10094767},
timestamp = {Fri, 10 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/WangYHHL23.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/iwslt/YangSZ0C23,
author = {Zhengdong Yang and
Shuichiro Shimizu and
Wangjin Zhou and
Sheng Li and
Chenhui Chu},
editor = {Elizabeth Salesky and
Marcello Federico and
Marine Carpuat},
title = {The Kyoto Speech-to-Speech Translation System for {IWSLT} 2023},
booktitle = {Proceedings of the 20th International Conference on Spoken Language
Translation, IWSLT@ACL 2023, Toronto, Canada (in-person and online),
13-14 July, 2023},
pages = {357--362},
publisher = {Association for Computational Linguistics},
year = {2023},
url = {https://doi.org/10.18653/v1/2023.iwslt-1.33},
doi = {10.18653/V1/2023.IWSLT-1.33},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iwslt/YangSZ0C23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmasia/ZhouYLC23,
author = {Wangjin Zhou and
Zhengdong Yang and
Sheng Li and
Chenhui Chu},
editor = {Wen{-}Huang Cheng and
Wei{-}Ta Chu and
Min{-}Chun Hu and
Jiaying Liu and
Munchurl Kim and
Wei Zhang},
title = {KyotoMOS: An Automatic {MOS} Scoring System for Speech Synthesis},
booktitle = {{ACM} Multimedia Asia Workshops, MMAsia 2023, Tainan, Taiwan, December
6-8, 2023},
pages = {7:1--7:3},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3611380.3628562},
doi = {10.1145/3611380.3628562},
timestamp = {Sat, 13 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mmasia/ZhouYLC23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmasia/Chen0LHCH23,
author = {Xiaojiao Chen and
Sheng Li and
Jiyi Li and
Hao Huang and
Yang Cao and
Liang He},
editor = {Wen{-}Huang Cheng and
Wei{-}Ta Chu and
Min{-}Chun Hu and
Jiaying Liu and
Munchurl Kim and
Wei Zhang},
title = {Reprogramming Self-supervised Learning-based Speech Representations
for Speaker Anonymization},
booktitle = {{ACM} Multimedia Asia 2023, MMAsia 2023, Tainan, Taiwan, December
6-8, 2023},
pages = {93:1--93:5},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3595916.3626366},
doi = {10.1145/3595916.3626366},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mmasia/Chen0LHCH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mmasia/ChenLLCHH23,
author = {Xiaojiao Chen and
Sheng Li and
Jiyi Li and
Yang Cao and
Hao Huang and
Liang He},
editor = {Wen{-}Huang Cheng and
Wei{-}Ta Chu and
Min{-}Chun Hu and
Jiaying Liu and
Munchurl Kim and
Wei Zhang},
title = {GhostVec: {A} New Threat to Speaker Privacy of End-to-End Speech Recognition
System},
booktitle = {{ACM} Multimedia Asia 2023, MMAsia 2023, Tainan, Taiwan, December
6-8, 2023},
pages = {94:1--94:5},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3595916.3626367},
doi = {10.1145/3595916.3626367},
timestamp = {Mon, 05 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/mmasia/ChenLLCHH23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-09210,
author = {Shuichiro Shimizu and
Chenhui Chu and
Sheng Li and
Sadao Kurohashi},
title = {Towards Speech Dialogue Translation Mediating Speakers of Different
Languages},
journal = {CoRR},
volume = {abs/2305.09210},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.09210},
doi = {10.48550/ARXIV.2305.09210},
eprinttype = {arXiv},
eprint = {2305.09210},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-09210.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ejasmp/QinWLDP22,
author = {Siqing Qin and
Longbiao Wang and
Sheng Li and
Jianwu Dang and
Lixin Pan},
title = {Improving low-resource Tibetan end-to-end {ASR} by multilingual and
multilevel unit modeling},
journal = {{EURASIP} J. Audio Speech Music. Process.},
volume = {2022},
number = {1},
pages = {2},
year = {2022},
url = {https://doi.org/10.1186/s13636-021-00233-4},
doi = {10.1186/S13636-021-00233-4},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ejasmp/QinWLDP22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/eusipco/LiLADLU22,
author = {Kai Li and
Xugang Lu and
Masato Akagi and
Jianwu Dang and
Sheng Li and
Masashi Unoki},
title = {Relationship Between Speakers' Physiological Structure and Acoustic
Speech Signals: Data-Driven Study Based on Frequency-Wise Attentional
Neural Network},
booktitle = {30th European Signal Processing Conference, {EUSIPCO} 2022, Belgrade,
Serbia, August 29 - Sept. 2, 2022},
pages = {379--383},
publisher = {{IEEE}},
year = {2022},
url = {https://ieeexplore.ieee.org/document/9909649},
timestamp = {Thu, 30 Mar 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/eusipco/LiLADLU22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/WangPHHL22,
author = {Kai Wang and
Yizhou Peng and
Hao Huang and
Ying Hu and
Sheng Li},
title = {Mining Hard Samples Locally And Globally For Improved Speech Separation},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {6037--6041},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9747797},
doi = {10.1109/ICASSP43922.2022.9747797},
timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/WangPHHL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LvWGLDPWDH22,
author = {Yongjie Lv and
Longbiao Wang and
Meng Ge and
Sheng Li and
Chenchen Ding and
Lixin Pan and
Yuguang Wang and
Jianwu Dang and
Kiyoshi Honda},
title = {Compressing Transformer-Based {ASR} Model by Task-Driven Loss and
Attention-Based Multi-Level Feature Distillation},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2022, Virtual and Singapore, 23-27 May 2022},
pages = {7992--7996},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/ICASSP43922.2022.9746113},
doi = {10.1109/ICASSP43922.2022.9746113},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LvWGLDPWDH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/Chen0H22,
author = {Xiaojiao Chen and
Sheng Li and
Hao Huang},
editor = {Mohammad Tanveer and
Sonali Agarwal and
Seiichi Ozawa and
Asif Ekbal and
Adam Jatowt},
title = {GhostVec: Directly Extracting Speaker Embedding from End-to-End Speech
Recognition Model Using Adversarial Examples},
booktitle = {Neural Information Processing - 29th International Conference, {ICONIP}
2022, Virtual Event, November 22-26, 2022, Proceedings, Part {VI}},
series = {Communications in Computer and Information Science},
volume = {1793},
pages = {482--492},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-981-99-1645-0\_40},
doi = {10.1007/978-981-99-1645-0\_40},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iconip/Chen0H22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/LiLLG22,
author = {Sheng Li and
Jiyi Li and
Qianying Liu and
Zhuo Gong},
editor = {Mohammad Tanveer and
Sonali Agarwal and
Seiichi Ozawa and
Asif Ekbal and
Adam Jatowt},
title = {An End-to-End Chinese and Japanese Bilingual Speech Recognition Systems
with Shared Character Decomposition},
booktitle = {Neural Information Processing - 29th International Conference, {ICONIP}
2022, Virtual Event, November 22-26, 2022, Proceedings, Part {VI}},
series = {Communications in Computer and Information Science},
volume = {1793},
pages = {493--503},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-981-99-1645-0\_41},
doi = {10.1007/978-981-99-1645-0\_41},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iconip/LiLLG22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/LiZLZYH22,
author = {Guangxing Li and
Wangjin Zhou and
Sheng Li and
Yi Zhao and
Jichen Yang and
Hao Huang},
editor = {Mohammad Tanveer and
Sonali Agarwal and
Seiichi Ozawa and
Asif Ekbal and
Adam Jatowt},
title = {Investigating Effective Domain Adaptation Method for Speaker Verification
Task},
booktitle = {Neural Information Processing - 29th International Conference, {ICONIP}
2022, Virtual Event, November 22-26, 2022, Proceedings, Part {VI}},
series = {Communications in Computer and Information Science},
volume = {1793},
pages = {517--527},
publisher = {Springer},
year = {2022},
url = {https://doi.org/10.1007/978-981-99-1645-0\_43},
doi = {10.1007/978-981-99-1645-0\_43},
timestamp = {Mon, 26 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iconip/LiZLZYH22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiW0DK22,
author = {Hao Shi and
Longbiao Wang and
Sheng Li and
Jianwu Dang and
Tatsuya Kawahara},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Monaural Speech Enhancement Based on Spectrogram Decomposition for
Convolutional Neural Network-sensitive Feature Extraction},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {221--225},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-11268},
doi = {10.21437/INTERSPEECH.2022-11268},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShiW0DK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiGWU0D22,
author = {Nan Li and
Meng Ge and
Longbiao Wang and
Masashi Unoki and
Sheng Li and
Jianwu Dang},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Global Signal-to-noise Ratio Estimation Based on Multi-subband Processing
Using Convolutional Neural Network},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {361--365},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-154},
doi = {10.21437/INTERSPEECH.2022-154},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiGWU0D22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YangW0LS22,
author = {Longfei Yang and
Wenqing Wei and
Sheng Li and
Jiyi Li and
Takahiro Shinozaki},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Augmented Adversarial Self-Supervised Learning for Early-Stage Alzheimer's
Speech Detection},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {541--545},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-943},
doi = {10.21437/INTERSPEECH.2022-943},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YangW0LS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Li0LALZZWDU22,
author = {Kai Li and
Sheng Li and
Xugang Lu and
Masato Akagi and
Meng Liu and
Lin Zhang and
Chang Zeng and
Longbiao Wang and
Jianwu Dang and
Masashi Unoki},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Data Augmentation Using McAdams-Coefficient-Based Speaker Anonymization
for Fake Audio Detection},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {664--668},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10088},
doi = {10.21437/INTERSPEECH.2022-10088},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Li0LALZZWDU22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/Kak0MCK22,
author = {Soky Kak and
Sheng Li and
Masato Mimura and
Chenhui Chu and
Tatsuya Kawahara},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Leveraging Simultaneous Translation for Enhancing Transcription of
Low-resource Language via Cross Attention Mechanism},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {1362--1366},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-343},
doi = {10.21437/INTERSPEECH.2022-343},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/Kak0MCK22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/QinW0LD22,
author = {Siqing Qin and
Longbiao Wang and
Sheng Li and
Yuqin Lin and
Jianwu Dang},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Finer-grained Modeling units-based Meta-Learning for Low-resource
Tibetan Speech Recognition},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {2133--2137},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10015},
doi = {10.21437/INTERSPEECH.2022-10015},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/QinW0LD22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/YangZC0DRZ22,
author = {Zhengdong Yang and
Wangjin Zhou and
Chenhui Chu and
Sheng Li and
Raj Dabre and
Raphael Rubino and
Yi Zhao},
editor = {Hanseok Ko and
John H. L. Hansen},
title = {Fusion of Self-supervised Learned Models for {MOS} Prediction},
booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech
Communication Association, Incheon, Korea, 18-22 September 2022},
pages = {5443--5447},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Interspeech.2022-10262},
doi = {10.21437/INTERSPEECH.2022-10262},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/YangZC0DRZ22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/lrec/0010LLG22,
author = {Sheng Li and
Jiyi Li and
Qianying Liu and
Zhuo Gong},
editor = {Nicoletta Calzolari and
Fr{\'{e}}d{\'{e}}ric B{\'{e}}chet and
Philippe Blache and
Khalid Choukri and
Christopher Cieri and
Thierry Declerck and
Sara Goggi and
Hitoshi Isahara and
Bente Maegaard and
Joseph Mariani and
H{\'{e}}l{\`{e}}ne Mazo and
Jan Odijk and
Stelios Piperidis},
title = {Adversarial Speech Generation and Natural Speech Recovery for Speech
Content Protection},
booktitle = {Proceedings of the Thirteenth Language Resources and Evaluation Conference,
{LREC} 2022, Marseille, France, 20-25 June 2022},
pages = {7291--7297},
publisher = {European Language Resources Association},
year = {2022},
url = {https://aclanthology.org/2022.lrec-1.792},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/lrec/0010LLG22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/KakGL22,
author = {Soky Kak and
Zhuo Gong and
Sheng Li},
title = {Nict-Tib1: {A} Public Speech Corpus Of Lhasa Dialect For Benchmarking
Tibetan Language Speech Recognition Systems},
booktitle = {25th Conference of the Oriental {COCOSDA} International Committee
for the Co-ordination and Standardisation of Speech Databases and
Assessment Techniques, {O-COCOSDA} 2022, Hanoi, Vietnam, November
24-26, 2022},
pages = {1--5},
publisher = {{IEEE}},
year = {2022},
url = {https://doi.org/10.1109/O-COCOSDA202257103.2022.9997917},
doi = {10.1109/O-COCOSDA202257103.2022.9997917},
timestamp = {Tue, 21 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ococosda/KakGL22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/GongSYS0KM22,
author = {Zhuo Gong and
Daisuke Saito and
Longfei Yang and
Takahiro Shinozaki and
Sheng Li and
Hisashi Kawai and
Nobuaki Minematsu},
editor = {Thomas Fang Zheng},
title = {Self-Adaptive Multilingual {ASR} Rescoring with Language Identification
and Unified Language Model},
booktitle = {Odyssey 2022: The Speaker and Language Recognition Workshop, 28 June
- 1 July 2022, Beijing, China},
pages = {415--420},
publisher = {{ISCA}},
year = {2022},
url = {https://doi.org/10.21437/Odyssey.2022-58},
doi = {10.21437/ODYSSEY.2022-58},
timestamp = {Sun, 02 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/GongSYS0KM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigdial/YangLLS22,
author = {Longfei Yang and
Jiyi Li and
Sheng Li and
Takahiro Shinozaki},
editor = {Oliver Lemon and
Dilek Hakkani{-}T{\"{u}}r and
Junyi Jessy Li and
Arash Ashrafzadeh and
Daniel Hern{\'{a}}ndez Garc{\'{\i}}a and
Malihe Alikhani and
David Vandyke and
Ondrej Dusek},
title = {Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention},
booktitle = {Proceedings of the 23rd Annual Meeting of the Special Interest Group
on Discourse and Dialogue, {SIGDIAL} 2022, Edinburgh, UK, 07-09 September
2022},
pages = {231--236},
publisher = {Association for Computational Linguistics},
year = {2022},
url = {https://doi.org/10.18653/v1/2022.sigdial-1.24},
doi = {10.18653/V1/2022.SIGDIAL-1.24},
timestamp = {Fri, 12 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigdial/YangLLS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-03855,
author = {Qianying Liu and
Yuhang Yang and
Zhuo Gong and
Sheng Li and
Chenchen Ding and
Nobuaki Minematsu and
Hao Huang and
Fei Cheng and
Sadao Kurohashi},
title = {Hierarchical Softmax for End-to-End Low-resource Multilingual Speech
Recognition},
journal = {CoRR},
volume = {abs/2204.03855},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.03855},
doi = {10.48550/ARXIV.2204.03855},
eprinttype = {arXiv},
eprint = {2204.03855},
timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-03855.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-04855,
author = {Zhengdong Yang and
Wangjin Zhou and
Chenhui Chu and
Sheng Li and
Raj Dabre and
Raphael Rubino and
Yi Zhao},
title = {Fusion of Self-supervised Learned Models for {MOS} Prediction},
journal = {CoRR},
volume = {abs/2204.04855},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.04855},
doi = {10.48550/ARXIV.2204.04855},
eprinttype = {arXiv},
eprint = {2204.04855},
timestamp = {Thu, 23 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-04855.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/jclc/KakMKCLDS21,
author = {Soky Kak and
Masato Mimura and
Tatsuya Kawahara and
Chenhui Chu and
Sheng Li and
Chenchen Ding and
Sethserey Sam},
title = {TriECCC: Trilingual Corpus of the Extraordinary Chambers in the Courts
of Cambodia for Speech Recognition and Translation Studies},
journal = {Int. J. Asian Lang. Process.},
volume = {31},
number = {3{\&}4},
pages = {2250007:1--2250007:21},
year = {2021},
url = {https://doi.org/10.1142/S2717554522500072},
doi = {10.1142/S2717554522500072},
timestamp = {Tue, 06 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jclc/KakMKCLDS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/KakLMCK21,
author = {Soky Kak and
Sheng Li and
Masato Mimura and
Chenhui Chu and
Tatsuya Kawahara},
title = {On the Use of Speaker Information for Automatic Speech Recognition
in Speaker-imbalanced Corpora},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {433--437},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689564},
timestamp = {Wed, 09 Feb 2022 09:03:08 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/KakLMCK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/ShiWLFDK21,
author = {Hao Shi and
Longbiao Wang and
Sheng Li and
Cunhang Fan and
Jianwu Dang and
Tatsuya Kawahara},
title = {Spectrograms Fusion-based End-to-end Robust Automatic Speech Recognition},
booktitle = {Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2021, Tokyo, Japan, December
14-17, 2021},
pages = {438--442},
publisher = {{IEEE}},
year = {2021},
url = {https://ieeexplore.ieee.org/document/9689650},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/ShiWLFDK21.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/icassp/ChenHLX21,
author = {Shunfei Chen and
Xinhui Hu and
Sheng Li and
Xinkang Xu},
title = {An Investigation of Using Hybrid Modeling Units for Improving End-to-End
Speech Recognition System},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6743--6747},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9414598},
doi = {10.1109/ICASSP39728.2021.9414598},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ChenHLX21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiWU0WGD21,
author = {Nan Li and
Longbiao Wang and
Masashi Unoki and
Sheng Li and
Rui Wang and
Meng Ge and
Jianwu Dang},
title = {Robust Voice Activity Detection Using a Masked Auditory Encoder Based
Convolutional Neural Network},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6828--6832},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9415045},
doi = {10.1109/ICASSP39728.2021.9415045},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LiWU0WGD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/HuangWHL21,
author = {Hao Huang and
Kai Wang and
Ying Hu and
Sheng Li},
title = {Encoder-Decoder Based Pitch Tracking and Joint Model Training for
Mandarin Tone Classification},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021},
pages = {6943--6947},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/ICASSP39728.2021.9413888},
doi = {10.1109/ICASSP39728.2021.9413888},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/HuangWHL21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/QiangSGYLW0D21,
author = {Luya Qiang and
Hao Shi and
Meng Ge and
Haoran Yin and
Nan Li and
Longbiao Wang and
Sheng Li and
Jianwu Dang},
editor = {Teddy Mantoro and
Minho Lee and
Media Anugerah Ayu and
Kok Wai Wong and
Achmad Nizar Hidayanto},
title = {Speech Dereverberation Based on Scale-Aware Mean Square Error Loss},
booktitle = {Neural Information Processing - 28th International Conference, {ICONIP}
2021, Sanur, Bali, Indonesia, December 8-12, 2021, Proceedings, Part
{V}},
series = {Communications in Computer and Information Science},
volume = {1516},
pages = {55--63},
publisher = {Springer},
year = {2021},
url = {https://doi.org/10.1007/978-3-030-92307-5\_7},
doi = {10.1007/978-3-030-92307-5\_7},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iconip/QiangSGYLW0D21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/LiuWLLDZD21,
author = {Dawei Liu and
Longbiao Wang and
Sheng Li and
Haoyu Li and
Chenchen Ding and
Ju Zhang and
Jianwu Dang},
editor = {Teddy Mantoro and
Minho Lee and
Media Anugerah Ayu and
Kok Wai Wong and
Achmad Nizar Hidayanto},
title = {Exploring Effective Speech Representation via {ASR} for High-Quality
End-to-End Multispeaker {TTS}},
booktitle = {Neural Information Processing - 28th International Conference, {ICONIP}
2021, Sanur, Bali, Indonesia, December 8-12, 2021, Proceedings, Part
{VI}},
series = {Communications in Computer and Information Science},
volume = {1517},
pages = {110--118},
publisher = {Springer},
year = {2021},
url = {https://doi.org/10.1007/978-3-030-92310-5\_13},
doi = {10.1007/978-3-030-92310-5\_13},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iconip/LiuWLLDZD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/YinSWQLGZD21,
author = {Haoran Yin and
Hao Shi and
Longbiao Wang and
Luya Qiang and
Sheng Li and
Meng Ge and
Gaoyan Zhang and
Jianwu Dang},
editor = {Teddy Mantoro and
Minho Lee and
Media Anugerah Ayu and
Kok Wai Wong and
Achmad Nizar Hidayanto},
title = {Simultaneous Progressive Filtering-Based Monaural Speech Enhancement},
booktitle = {Neural Information Processing - 28th International Conference, {ICONIP}
2021, Sanur, Bali, Indonesia, December 8-12, 2021, Proceedings, Part
{V}},
series = {Communications in Computer and Information Science},
volume = {1516},
pages = {213--221},
publisher = {Springer},
year = {2021},
url = {https://doi.org/10.1007/978-3-030-92307-5\_25},
doi = {10.1007/978-3-030-92307-5\_25},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iconip/YinSWQLGZD21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangHHH021,
author = {Kai Wang and
Hao Huang and
Ying Hu and
Zhihua Huang and
Sheng Li},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {End-to-End Speech Separation Using Orthogonal Representation in Complex
and Real Time-Frequency Domain},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {3046--3050},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-504},
doi = {10.21437/INTERSPEECH.2021-504},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangHHH021.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/WangYHLX21,
author = {Ding Wang and
Shuaishuai Ye and
Xinhui Hu and
Sheng Li and
Xinkang Xu},
editor = {Hynek Hermansky and
Honza Cernock{\'{y}} and
Luk{\'{a}}s Burget and
Lori Lamel and
Odette Scharenborg and
Petr Motl{\'{\i}}cek},
title = {An End-to-End Dialect Identification System with Transfer Learning
from a Multilingual Automatic Speech Recognition Model},
booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech
Communication Association, Brno, Czechia, 30 August - 3 September
2021},
pages = {3266--3270},
publisher = {{ISCA}},
year = {2021},
url = {https://doi.org/10.21437/Interspeech.2021-374},
doi = {10.21437/INTERSPEECH.2021-374},
timestamp = {Wed, 21 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/WangYHLX21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/KakMK0DCS21,
author = {Soky Kak and
Masato Mimura and
Tatsuya Kawahara and
Sheng Li and
Chenchen Ding and
Chenhui Chu and
Sethserey Sam},
title = {Khmer Speech Translation Corpus of the Extraordinary Chambers in the
Courts of Cambodia {(ECCC)}},
booktitle = {24th Conference of the Oriental {COCOSDA} International Committee
for the Co-ordination and Standardisation of Speech Databases and
Assessment Techniques, {O-COCOSDA} 2021, Singapore, November 18-20,
2021},
pages = {122--127},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.1109/O-COCOSDA202152914.2021.9660421},
doi = {10.1109/O-COCOSDA202152914.2021.9660421},
timestamp = {Wed, 07 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ococosda/KakMK0DCS21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/ShenL0K20,
author = {Peng Shen and
Xugang Lu and
Sheng Li and
Hisashi Kawai},
title = {Knowledge Distillation-Based Representation Learning for Short-Utterance
Spoken Language Identification},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {28},
pages = {2674--2683},
year = {2020},
url = {https://doi.org/10.1109/TASLP.2020.3023627},
doi = {10.1109/TASLP.2020.3023627},
timestamp = {Tue, 16 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/taslp/ShenL0K20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccs/HanCLMY20,
author = {Yaowei Han and
Yang Cao and
Sheng Li and
Qiang Ma and
Masatoshi Yoshikawa},
editor = {Jay Ligatti and
Xinming Ou and
Jonathan Katz and
Giovanni Vigna},
title = {Voice-Indistinguishability - Protecting Voiceprint with Differential
Privacy under an Untrusted Server},
booktitle = {{CCS} '20: 2020 {ACM} {SIGSAC} Conference on Computer and Communications
Security, Virtual Event, USA, November 9-13, 2020},
pages = {2125--2127},
publisher = {{ACM}},
year = {2020},
url = {https://doi.org/10.1145/3372297.3420025},
doi = {10.1145/3372297.3420025},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ccs/HanCLMY20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LinWD0D20,
author = {Yuqin Lin and
Longbiao Wang and
Jianwu Dang and
Sheng Li and
Chenchen Ding},
title = {End-to-End Articulatory Modeling for Dysarthric Articulatory Attribute
Detection},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7349--7353},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054233},
doi = {10.1109/ICASSP40776.2020.9054233},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/LinWD0D20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ShiWG0D20,
author = {Hao Shi and
Longbiao Wang and
Meng Ge and
Sheng Li and
Jianwu Dang},
title = {Spectrograms Fusion with Minimum Difference Masks Estimation for Monaural
Speech Dereverberation},
booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020},
pages = {7544--7548},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICASSP40776.2020.9054661},
doi = {10.1109/ICASSP40776.2020.9054661},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/ShiWG0D20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icmcs/Han000Y20,
author = {Yaowei Han and
Sheng Li and
Yang Cao and
Qiang Ma and
Masatoshi Yoshikawa},
title = {Voice-Indistinguishability: Protecting Voiceprint In Privacy-Preserving
Speech Data Release},
booktitle = {{IEEE} International Conference on Multimedia and Expo, {ICME} 2020,
London, UK, July 6-10, 2020},
pages = {1--6},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/ICME46284.2020.9102875},
doi = {10.1109/ICME46284.2020.9102875},
timestamp = {Sat, 30 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icmcs/Han000Y20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iconip/GuoWLZGWDH20,
author = {Shaotong Guo and
Longbiao Wang and
Sheng Li and
Ju Zhang and
Cheng Gong and
Yuguang Wang and
Jianwu Dang and
Kiyoshi Honda},
editor = {Haiqin Yang and
Kitsuchart Pasupa and
Andrew Chi{-}Sing Leung and
James T. Kwok and
Jonathan H. Chan and
Irwin King},
title = {Investigation of Effectively Synthesizing Code-Switched Speech Using
Highly Imbalanced Mix-Lingual Data},
booktitle = {Neural Information Processing - 27th International Conference, {ICONIP}
2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part {I}},
series = {Lecture Notes in Computer Science},
volume = {12532},
pages = {36--47},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-3-030-63830-6\_4},
doi = {10.1007/978-3-030-63830-6\_4},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iconip/GuoWLZGWDH20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShiW0DGLDS20,
author = {Hao Shi and
Longbiao Wang and
Sheng Li and
Chenchen Ding and
Meng Ge and
Nan Li and
Jianwu Dang and
Hiroshi Seki},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Singing Voice Extraction with Attention-Based Spectrograms Fusion},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {2412--2416},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-1043},
doi = {10.21437/INTERSPEECH.2020-1043},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ShiW0DGLDS20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LinW0DD20,
author = {Yuqin Lin and
Longbiao Wang and
Sheng Li and
Jianwu Dang and
Chenchen Ding},
editor = {Helen Meng and
Bo Xu and
Thomas Fang Zheng},
title = {Staged Knowledge Distillation for End-to-End Dysarthric Speech Recognition
and Speech Attribute Transcription},
booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech
Communication Association, Virtual Event, Shanghai, China, 25-29 October
2020},
pages = {4791--4795},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Interspeech.2020-1755},
doi = {10.21437/INTERSPEECH.2020-1755},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/LinW0DD20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ococosda/ThidaHO0D20,
author = {Aye Thida and
Nway Nway Han and
Sheinn Thawtar Oo and
Sheng Li and
Chenchen Ding},
title = {{VOIS:} The First Speech Therapy App Specifically Designed for Myanmar
Hearing-Impaired Children},
booktitle = {23rd Conference of the Oriental {COCOSDA} International Committee
for the Co-ordination and Standardisation of Speech Databases and
Assessment Techniques, {O-COCOSDA} 2020, Yangon, Myanmar, November
5-7, 2020},
pages = {151--154},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/O-COCOSDA50338.2020.9295024},
doi = {10.1109/O-COCOSDA50338.2020.9295024},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ococosda/ThidaHO0D20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/ShenLS0K20,
author = {Peng Shen and
Xugang Lu and
Komei Sugiura and
Sheng Li and
Hisashi Kawai},
editor = {Kong{-}Aik Lee and
Takafumi Koshinaka and
Koichi Shinoda},
title = {Compensation on x-vector for Short Utterance Spoken Language Identification},
booktitle = {Odyssey 2020: The Speaker and Language Recognition Workshop, 1-5 November
2020, Tokyo, Japan},
pages = {47--52},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Odyssey.2020-7},
doi = {10.21437/ODYSSEY.2020-7},
timestamp = {Tue, 16 Nov 2021 11:36:03 +0100},
biburl = {https://dblp.org/rec/conf/odyssey/ShenLS0K20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/odyssey/0010LDSK20,
author = {Sheng Li and
Xugang Lu and
Raj Dabre and
Peng Shen and
Hisashi Kawai},
editor = {Kong{-}Aik Lee and
Takafumi Koshinaka and
Koichi Shinoda},
title = {Joint Training End-to-End Speech Recognition Systems with Speaker
Attributes},
booktitle = {Odyssey 2020: The Speaker and Language Recognition Workshop, 1-5 November
2020, Tokyo, Japan},
pages = {385--390},
publisher = {{ISCA}},
year = {2020},
url = {https://doi.org/10.21437/Odyssey.2020-54},
doi = {10.21437/ODYSSEY.2020-54},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/odyssey/0010LDSK20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:series/sbcs/Lu0F20,
author = {Xugang Lu and
Sheng Li and
Masakiyo Fujimoto},
editor = {Yutaka Kidawara and
Eiichiro Sumita and
Hisashi Kawai},
title = {Automatic Speech Recognition},
booktitle = {Speech-to-Speech Translation},
series = {Springer Briefs in Computer Science},
pages = {21--38},
publisher = {Springer},
year = {2020},
url = {https://doi.org/10.1007/978-981-15-0595-9\_2},
doi = {10.1007/978-981-15-0595-9\_2},
timestamp = {Fri, 27 Dec 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/series/sbcs/Lu0F20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2004-07442,
author = {Yaowei Han and
Sheng Li and
Yang Cao and
Qiang Ma and
Masatoshi Yoshikawa},
title = {Voice-Indistinguishability: Protecting Voiceprint in Privacy-Preserving
Speech Data Release},
journal = {CoRR},
volume = {abs/2004.07442},
year = {2020},
url = {https://arxiv.org/abs/2004.07442},
eprinttype = {arXiv},
eprint = {2004.07442},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2004-07442.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/PanLWD19,
author = {Lixin Pan and
Sheng Li and
Longbiao Wang and
Jianwu Dang},
title = {Effective Training End-to-End {ASR} systems for Low-resource Lhasa
Dialect of Tibetan Language},
booktitle = {2019 Asia-Pacific Signal and Information Processing Association Annual
Summit and Conference, {APSIPA} {ASC} 2019, Lanzhou, China, November
18-21, 2019},
pages = {1152--1156},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023100},
doi = {10.1109/APSIPAASC47483.2019.9023100},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/apsipa/PanLWD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/apsipa/Soky0KS19,
author = {Soky Kak and
Sheng Li and
Tatsuya Kawahara and
Sopheap Seng},
title = {Multi-lingual Transformer Training for Khmer Automatic 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 = {1893--1896},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/APSIPAASC47483.2019.9023137},
doi = {10.1109/APSIPAASC47483.2019.9023137},
timestamp = {Sun, 31 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/apsipa/Soky0KS19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/ShenL0K19,
author = {Peng Shen and
Xugang Lu and
Sheng Li and
Hisashi Kawai},
title = {Interactive Learning of Teacher-student Model for Short Utterance
Spoken Language Identification},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {5981--5985},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8683371},
doi = {10.1109/ICASSP.2019.8683371},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/ShenL0K19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/Takashima0K19,
author = {Ryoichi Takashima and
Sheng Li and
Hisashi Kawai},
title = {Investigation of Sequence-level Knowledge Distillation Methods for
{CTC} Acoustic Models},
booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing,
{ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019},
pages = {6156--6160},
publisher = {{IEEE}},
year = {2019},
url = {https://doi.org/10.1109/ICASSP.2019.8682671},
doi = {10.1109/ICASSP.2019.8682671},
timestamp = {Sat, 19 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/Takashima0K19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/0010DLSKK19,
author = {Sheng Li and
Chenchen Ding and
Xugang Lu and
Peng Shen and
Tatsuya Kawahara and
Hisashi Kawai},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {End-to-End Articulatory Attribute Modeling for Low-Resource Multilingual
Speech Recognition},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {2145--2149},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2092},
doi = {10.21437/INTERSPEECH.2019-2092},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/0010DLSKK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiLDSKK19,
author = {Sheng Li and
Xugang Lu and
Chenchen Ding and
Peng Shen and
Tatsuya Kawahara and
Hisashi Kawai},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Investigating Radical-Based End-to-End Speech Recognition Systems
for Chinese Dialects and Japanese},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {2200--2204},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2104},
doi = {10.21437/INTERSPEECH.2019-2104},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiLDSKK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LuS00K19,
author = {Xugang Lu and
Peng Shen and
Sheng Li and
Yu Tsao and
Hisashi Kawai},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Class-Wise Centroid Distance Metric Learning for Acoustic Event Detection},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {3614--3618},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2271},
doi = {10.21437/INTERSPEECH.2019-2271},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/LuS00K19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiRLSKK19,
author = {Sheng Li and
Raj Dabre and
Xugang Lu and
Peng Shen and
Tatsuya Kawahara and
Hisashi Kawai},
editor = {Gernot Kubin and
Zdravko Kacic},
title = {Improving Transformer-Based Speech Recognition Systems with Compressed
Structure and Speech Attributes Augmentation},
booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech
Communication Association, Graz, Austria, 15-19 September 2019},
pages = {4400--4404},
publisher = {{ISCA}},
year = {2019},
url = {https://doi.org/10.21437/Interspeech.2019-2112},
doi = {10.21437/INTERSPEECH.2019-2112},
timestamp = {Wed, 04 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiRLSKK19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1912-12011,
author = {Xugang Lu and
Peng Shen and
Sheng Li and
Yu Tsao and
Hisashi Kawai},
title = {Deep progressive multi-scale attention for acoustic event classification},
journal = {CoRR},
volume = {abs/1912.12011},
year = {2019},
url = {http://arxiv.org/abs/1912.12011},
eprinttype = {arXiv},
eprint = {1912.12011},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1912-12011.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakashimaLK18,
author = {Ryoichi Takashima and
Sheng Li and
Hisashi Kawai},
title = {An Investigation of a Knowledge Distillation Method for {CTC} Acoustic
Models},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5809--5813},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461995},
doi = {10.1109/ICASSP.2018.8461995},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TakashimaLK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TakashimaLK18a,
author = {Ryoichi Takashima and
Sheng Li and
Hisashi Kawai},
title = {{CTC} Loss Function with a Unit-Level Ambiguity Penalty},
booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018},
pages = {5909--5913},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/ICASSP.2018.8461762},
doi = {10.1109/ICASSP.2018.8461762},
timestamp = {Wed, 25 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icassp/TakashimaLK18a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LuSLTK18,
author = {Xugang Lu and
Peng Shen and
Sheng Li and
Yu Tsao and
Hisashi Kawai},
editor = {B. Yegnanarayana},
title = {Temporal Attentive Pooling for Acoustic Event Detection},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {1354--1357},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1552},
doi = {10.21437/INTERSPEECH.2018-1552},
timestamp = {Fri, 21 May 2021 08:16:43 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LuSLTK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShenLLK18,
author = {Peng Shen and
Xugang Lu and
Sheng Li and
Hisashi Kawai},
editor = {B. Yegnanarayana},
title = {Feature Representation of Short Utterances Based on Knowledge Distillation
for Spoken Language Identification},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {1813--1817},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1519},
doi = {10.21437/INTERSPEECH.2018-1519},
timestamp = {Fri, 29 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/interspeech/ShenLLK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiLTSKK18,
author = {Sheng Li and
Xugang Lu and
Ryoichi Takashima and
Peng Shen and
Tatsuya Kawahara and
Hisashi Kawai},
editor = {B. Yegnanarayana},
title = {Improving CTC-based Acoustic Model with Very Deep Residual Time-delay
Neural Networks},
booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech
Communication Association, Hyderabad, India, 2-6 September 2018},
pages = {3708--3712},
publisher = {{ISCA}},
year = {2018},
url = {https://doi.org/10.21437/Interspeech.2018-1475},
doi = {10.21437/INTERSPEECH.2018-1475},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiLTSKK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/slt/0010LTSKK18,
author = {Sheng Li and
Xugang Lu and
Ryoichi Takashima and
Peng Shen and
Tatsuya Kawahara and
Hisashi Kawai},
title = {Improving Very Deep Time-Delay Neural Network With Vertical-Attention
For Effectively Training CTC-Based {ASR} Systems},
booktitle = {2018 {IEEE} Spoken Language Technology Workshop, {SLT} 2018, Athens,
Greece, December 18-21, 2018},
pages = {77--83},
publisher = {{IEEE}},
year = {2018},
url = {https://doi.org/10.1109/SLT.2018.8639675},
doi = {10.1109/SLT.2018.8639675},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/slt/0010LTSKK18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asru/LiLSTKK17,
author = {Sheng Li and
Xugang Lu and
Peng Shen and
Ryoichi Takashima and
Tatsuya Kawahara and
Hisashi Kawai},
title = {Incremental training and constructing the very deep convolutional
residual network acoustic models},
booktitle = {2017 {IEEE} Automatic Speech Recognition and Understanding Workshop,
{ASRU} 2017, Okinawa, Japan, December 16-20, 2017},
pages = {222--227},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ASRU.2017.8268939},
doi = {10.1109/ASRU.2017.8268939},
timestamp = {Sun, 25 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/asru/LiLSTKK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiLSMK17,
author = {Sheng Li and
Xugang Lu and
Shinsuke Sakai and
Masato Mimura and
Tatsuya Kawahara},
title = {Semi-supervised ensemble {DNN} acoustic model training},
booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017},
pages = {5270--5274},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ICASSP.2017.7953162},
doi = {10.1109/ICASSP.2017.7953162},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiLSMK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/ShenLLK17,
author = {Peng Shen and
Xugang Lu and
Sheng Li and
Hisashi Kawai},
editor = {Francisco Lacerda},
title = {Conditional Generative Adversarial Nets Classifier for Spoken Language
Identification},
booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech
Communication Association, Stockholm, Sweden, August 20-24, 2017},
pages = {2814--2818},
publisher = {{ISCA}},
year = {2017},
url = {https://doi.org/10.21437/Interspeech.2017-553},
doi = {10.21437/INTERSPEECH.2017-553},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/ShenLLK17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@phdthesis{DBLP:phd/jp/Li16,
author = {Sheng Li},
title = {Speech Recognition Enhanced by Lightly-supervised and Semi-supervised
Acoustic Model Training},
school = {Kyoto University, Japan},
year = {2016},
url = {https://ci.nii.ac.jp/naid/500001007801},
doi = {10.14989/DOCTOR.K19849},
timestamp = {Tue, 24 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/phd/jp/Li16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/taslp/LiAK16,
author = {Sheng Li and
Yuya Akita and
Tatsuya Kawahara},
title = {Semi-Supervised Acoustic Model Training by Discriminative Data Selection
From Multiple {ASR} Systems' Hypotheses},
journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.},
volume = {24},
number = {9},
pages = {1524--1534},
year = {2016},
url = {https://doi.org/10.1109/TASLP.2016.2562505},
doi = {10.1109/TASLP.2016.2562505},
timestamp = {Fri, 13 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/taslp/LiAK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/LiAK16,
author = {Sheng Li and
Yuya Akita and
Tatsuya Kawahara},
title = {Data selection from multiple {ASR} systems' hypotheses for unsupervised
acoustic model training},
booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal
Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016},
pages = {5875--5879},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/ICASSP.2016.7472804},
doi = {10.1109/ICASSP.2016.7472804},
timestamp = {Wed, 16 Oct 2019 14:14:52 +0200},
biburl = {https://dblp.org/rec/conf/icassp/LiAK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/LiLMAK16,
author = {Sheng Li and
Xugang Lu and
Shinsuke Mori and
Yuya Akita and
Tatsuya Kawahara},
title = {Confidence estimation for speech recognition systems using conditional
random fields trained with partially annotated data},
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.2016.7918419},
doi = {10.1109/ISCSLP.2016.7918419},
timestamp = {Wed, 16 Oct 2019 14:14:48 +0200},
biburl = {https://dblp.org/rec/conf/iscslp/LiLMAK16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ieicet/LiAK15,
author = {Sheng Li and
Yuya Akita and
Tatsuya Kawahara},
title = {Automatic Lecture Transcription Based on Discriminative Data Selection
for Lightly Supervised Acoustic Model Training},
journal = {{IEICE} Trans. Inf. Syst.},
volume = {98-D},
number = {8},
pages = {1545--1552},
year = {2015},
url = {https://doi.org/10.1587/transinf.2015EDP7047},
doi = {10.1587/TRANSINF.2015EDP7047},
timestamp = {Sat, 11 Apr 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ieicet/LiAK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiLAK15,
author = {Sheng Li and
Xugang Lu and
Yuya Akita and
Tatsuya Kawahara},
title = {Ensemble speaker modeling using speaker adaptive training deep neural
network for speaker adaptation},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {2892--2896},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-608},
doi = {10.21437/INTERSPEECH.2015-608},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiLAK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiAK15,
author = {Sheng Li and
Yuya Akita and
Tatsuya Kawahara},
title = {Discriminative data selection for lightly supervised training of acoustic
model using closed caption texts},
booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech
Communication Association, Dresden, Germany, September 6-10, 2015},
pages = {3526--3530},
publisher = {{ISCA}},
year = {2015},
url = {https://doi.org/10.21437/Interspeech.2015-699},
doi = {10.21437/INTERSPEECH.2015-699},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiAK15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iscslp/LiAK14,
author = {Sheng Li and
Yuya Akita and
Tatsuya Kawahara},
editor = {Minghui Dong and
Jianhua Tao and
Haizhou Li and
Thomas Fang Zheng and
Yanfeng Lu},
title = {Corpus and transcription system of Chinese Lecture Room},
booktitle = {The 9th International Symposium on Chinese Spoken Language Processing,
Singapore, September 12-14, 2014},
pages = {442--445},
publisher = {{IEEE}},
year = {2014},
url = {https://doi.org/10.1109/ISCSLP.2014.6936595},
doi = {10.1109/ISCSLP.2014.6936595},
timestamp = {Mon, 18 Mar 2024 17:29:23 +0100},
biburl = {https://dblp.org/rec/conf/iscslp/LiAK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/speech/WangCLM12,
author = {Lan Wang and
Hui Chen and
Sheng Li and
Helen M. Meng},
title = {Phoneme-level articulatory animation in pronunciation training},
journal = {Speech Commun.},
volume = {54},
number = {7},
pages = {845--856},
year = {2012},
url = {https://doi.org/10.1016/j.specom.2012.02.003},
doi = {10.1016/J.SPECOM.2012.02.003},
timestamp = {Thu, 29 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/speech/WangCLM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/interspeech/LiW12,
author = {Sheng Li and
Lan Wang},
title = {Cross Linguistic Comparison of Mandarin and English {EMA} Articulatory
Data},
booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech
Communication Association, Portland, Oregon, USA, September 9-13,
2012},
pages = {903--906},
publisher = {{ISCA}},
year = {2012},
url = {https://doi.org/10.21437/Interspeech.2012-272},
doi = {10.21437/INTERSPEECH.2012-272},
timestamp = {Fri, 23 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/interspeech/LiW12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ialp/LiWQ11,
author = {Sheng Li and
Lan Wang and
En Qi},
title = {The Phoneme-Level Articulator Dynamics for Pronunciation Animation},
booktitle = {International Conference on Asian Language Processing, {IALP} 2011,
Penang, Malaysia, 15-17 November, 2011},
pages = {283--286},
publisher = {{IEEE} Computer Society},
year = {2011},
url = {https://doi.org/10.1109/IALP.2011.13},
doi = {10.1109/IALP.2011.13},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ialp/LiWQ11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
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.
last updated on 2024-04-19 19:32 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
