Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Xunying Liu
@article{DBLP:journals/taslp/JinGDWHLL24, author = {Zengrui Jin and Mengzhe Geng and Jiajun Deng and Tianzi Wang and Shujie Hu and Guinan Li and Xunying Liu}, title = {Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {32}, pages = {413--429}, year = {2024}, url = {https://doi.org/10.1109/TASLP.2023.3323888}, doi = {10.1109/TASLP.2023.3323888}, timestamp = {Sun, 10 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/JinGDWHLL24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-00662, author = {Huimeng Wang and Zengrui Jin and Mengzhe Geng and Shujie Hu and Guinan Li and Tianzi Wang and Haoning Xu and Xunying Liu}, title = {Enhancing Pre-trained {ASR} System Fine-tuning for Dysarthric Speech Recognition using Adversarial Data Augmentation}, journal = {CoRR}, volume = {abs/2401.00662}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.00662}, doi = {10.48550/ARXIV.2401.00662}, eprinttype = {arXiv}, eprint = {2401.00662}, timestamp = {Mon, 15 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-00662.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-04152, author = {Jiawen Kang and Lingwei Meng and Mingyu Cui and Haohan Guo and Xixin Wu and Xunying Liu and Helen Meng}, title = {Cross-Speaker Encoding Network for Multi-Talker Speech Recognition}, journal = {CoRR}, volume = {abs/2401.04152}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.04152}, doi = {10.48550/ARXIV.2401.04152}, eprinttype = {arXiv}, eprint = {2401.04152}, timestamp = {Wed, 24 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-04152.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-17796, author = {Xueyuan Chen and Yuejiao Wang and Xixin Wu and Disong Wang and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Exploiting Audio-Visual Features with Pretrained AV-HuBERT for Multi-Modal Dysarthric Speech Reconstruction}, journal = {CoRR}, volume = {abs/2401.17796}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.17796}, doi = {10.48550/ARXIV.2401.17796}, eprinttype = {arXiv}, eprint = {2401.17796}, timestamp = {Wed, 07 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-17796.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/DengXWCXJLHL23, author = {Jiajun Deng and Xurong Xie and Tianzi Wang and Mingyu Cui and Boyang Xue and Zengrui Jin and Guinan Li and Shujie Hu and Xunying Liu}, title = {Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {31}, pages = {1175--1190}, year = {2023}, url = {https://doi.org/10.1109/TASLP.2023.3250842}, doi = {10.1109/TASLP.2023.3250842}, timestamp = {Tue, 28 Mar 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/DengXWCXJLHL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/LiDGJWHCML23, author = {Guinan Li and Jiajun Deng and Mengzhe Geng and Zengrui Jin and Tianzi Wang and Shujie Hu and Mingyu Cui and Helen Meng and Xunying Liu}, title = {Audio-Visual End-to-End Multi-Channel Speech Separation, Dereverberation and Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {31}, pages = {2707--2723}, year = {2023}, url = {https://doi.org/10.1109/TASLP.2023.3294705}, doi = {10.1109/TASLP.2023.3294705}, timestamp = {Sat, 05 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/LiDGJWHCML23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/WuLLWLM23, author = {Xixin Wu and Hui Lu and Kun Li and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Hiformer: Sequence Modeling Networks With Hierarchical Attention Mechanisms}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {31}, pages = {3993--4003}, year = {2023}, url = {https://doi.org/10.1109/TASLP.2023.3313428}, doi = {10.1109/TASLP.2023.3313428}, timestamp = {Sun, 31 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/WuLLWLM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuXJGWCDLM23, author = {Shujie Hu and Xurong Xie and Zengrui Jin and Mengzhe Geng and Yi Wang and Mingyu Cui and Jiajun Deng and Xunying Liu and Helen Meng}, title = {Exploring Self-Supervised Pre-Trained {ASR} Models for Dysarthric and Elderly 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/ICASSP49357.2023.10097275}, doi = {10.1109/ICASSP49357.2023.10097275}, timestamp = {Sun, 05 Nov 2023 16:51:21 +0100}, biburl = {https://dblp.org/rec/conf/icassp/HuXJGWCDLM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/JinXGWHDLL23, author = {Zengrui Jin and Xurong Xie and Mengzhe Geng and Tianzi Wang and Shujie Hu and Jiajun Deng and Guinan Li and Xunying Liu}, title = {Adversarial Data Augmentation Using {VAE-GAN} for Disordered 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/ICASSP49357.2023.10095547}, doi = {10.1109/ICASSP49357.2023.10095547}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/JinXGWHDLL23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiSLZLWLM23, author = {Jinchao Li and Kaitao Song and Junan Li and Bo Zheng and Dongsheng Li and Xixin Wu and Xunying Liu and Helen Meng}, title = {Leveraging Pretrained Representations With Task-Related Keywords for Alzheimer's Disease Detection}, 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/ICASSP49357.2023.10096205}, doi = {10.1109/ICASSP49357.2023.10096205}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiSLZLWLM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiWSLLM23, author = {Jinchao Li and Xixin Wu and Kaitao Song and Dongsheng Li and Xunying Liu and Helen Meng}, title = {A Hierarchical Regression Chain Framework for Affective Vocal Burst 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/ICASSP49357.2023.10096395}, doi = {10.1109/ICASSP49357.2023.10096395}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiWSLLM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangDWZHLM23, author = {Yi Wang and Jiajun Deng and Tianzi Wang and Bo Zheng and Shoukang Hu and Xunying Liu and Helen Meng}, title = {Exploiting Prompt Learning with Pre-Trained Language Models for Alzheimer's Disease Detection}, 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/ICASSP49357.2023.10095993}, doi = {10.1109/ICASSP49357.2023.10095993}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/WangDWZHLM23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XieLCW23, author = {Xurong Xie and Xunying Liu and Hui Chen and Hongan Wang}, title = {Unsupervised Model-Based Speaker Adaptation of End-To-End Lattice-Free {MMI} Model for 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/ICASSP49357.2023.10095083}, doi = {10.1109/ICASSP49357.2023.10095083}, timestamp = {Sun, 05 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XieLCW23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-07521, author = {Jiajun Deng and Xurong Xie and Tianzi Wang and Mingyu Cui and Boyang Xue and Zengrui Jin and Guinan Li and Shujie Hu and Xunying Liu}, title = {Confidence Score Based Speaker Adaptation of Conformer Speech Recognition Systems}, journal = {CoRR}, volume = {abs/2302.07521}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.07521}, doi = {10.48550/ARXIV.2302.07521}, eprinttype = {arXiv}, eprint = {2302.07521}, timestamp = {Mon, 20 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-07521.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-14564, author = {Shujie Hu and Xurong Xie and Zengrui Jin and Mengzhe Geng and Yi Wang and Mingyu Cui and Jiajun Deng and Xunying Liu and Helen Meng}, title = {Exploring Self-supervised Pre-trained {ASR} Models For Dysarthric and Elderly Speech Recognition}, journal = {CoRR}, volume = {abs/2302.14564}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.14564}, doi = {10.48550/ARXIV.2302.14564}, eprinttype = {arXiv}, eprint = {2302.14564}, timestamp = {Thu, 02 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-14564.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-08019, author = {Jinchao Li and Kaitao Song and Junan Li and Bo Zheng and Dongsheng Li and Xixin Wu and Xunying Liu and Helen Meng}, title = {Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease Detection}, journal = {CoRR}, volume = {abs/2303.08019}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.08019}, doi = {10.48550/ARXIV.2303.08019}, eprinttype = {arXiv}, eprint = {2303.08019}, timestamp = {Thu, 20 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-08019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-08027, author = {Jinchao Li and Xixin Wu and Kaitao Song and Dongsheng Li and Xunying Liu and Helen Meng}, title = {A Hierarchical Regression Chain Framework for Affective Vocal Burst Recognition}, journal = {CoRR}, volume = {abs/2303.08027}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.08027}, doi = {10.48550/ARXIV.2303.08027}, eprinttype = {arXiv}, eprint = {2303.08027}, timestamp = {Thu, 20 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-08027.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-10659, author = {Mengzhe Geng and Zengrui Jin and Tianzi Wang and Shujie Hu and Jiajun Deng and Mingyu Cui and Guinan Li and Jianwei Yu and Xurong Xie and Xunying Liu}, title = {Use of Speech Impairment Severity for Dysarthric Speech Recognition}, journal = {CoRR}, volume = {abs/2305.10659}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.10659}, doi = {10.48550/ARXIV.2305.10659}, eprinttype = {arXiv}, eprint = {2305.10659}, timestamp = {Wed, 24 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-10659.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-13307, author = {Mingyu Cui and Jiawen Kang and Jiajun Deng and Xi Yin and Yutao Xie and Xie Chen and Xunying Liu}, title = {Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems}, journal = {CoRR}, volume = {abs/2306.13307}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.13307}, doi = {10.48550/ARXIV.2306.13307}, eprinttype = {arXiv}, eprint = {2306.13307}, timestamp = {Tue, 04 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-13307.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-14608, author = {Jiajun Deng and Guinan Li and Xurong Xie and Zengrui Jin and Mingyu Cui and Tianzi Wang and Shujie Hu and Mengzhe Geng and Xunying Liu}, title = {Factorised Speaker-environment Adaptive Training of Conformer Speech Recognition Systems}, journal = {CoRR}, volume = {abs/2306.14608}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.14608}, doi = {10.48550/ARXIV.2306.14608}, eprinttype = {arXiv}, eprint = {2306.14608}, timestamp = {Wed, 28 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-14608.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2306-15265, author = {Tianzi Wang and Shoukang Hu and Jiajun Deng and Zengrui Jin and Mengzhe Geng and Yi Wang and Helen Meng and Xunying Liu}, title = {Hyper-parameter Adaptation of Conformer {ASR} Systems for Elderly and Dysarthric Speech Recognition}, journal = {CoRR}, volume = {abs/2306.15265}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2306.15265}, doi = {10.48550/ARXIV.2306.15265}, eprinttype = {arXiv}, eprint = {2306.15265}, timestamp = {Mon, 03 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2306-15265.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2307-02909, author = {Guinan Li and Jiajun Deng and Mengzhe Geng and Zengrui Jin and Tianzi Wang and Shujie Hu and Mingyu Cui and Helen Meng and Xunying Liu}, title = {Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition}, journal = {CoRR}, volume = {abs/2307.02909}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2307.02909}, doi = {10.48550/ARXIV.2307.02909}, eprinttype = {arXiv}, eprint = {2307.02909}, timestamp = {Mon, 10 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2307-02909.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-08641, author = {Zengrui Jin and Xurong Xie and Tianzi Wang and Mengzhe Geng and Jiajun Deng and Guinan Li and Shujie Hu and Xunying Liu}, title = {Towards Automatic Data Augmentation for Disordered Speech Recognition}, journal = {CoRR}, volume = {abs/2312.08641}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.08641}, doi = {10.48550/ARXIV.2312.08641}, eprinttype = {arXiv}, eprint = {2312.08641}, timestamp = {Tue, 09 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-08641.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ficn/WingfieldZDFTLWMS22, author = {Cai Wingfield and Chao Zhang and Barry Devereux and Elisabeth Fonteneau and Andrew Thwaites and Xunying Liu and Philip C. Woodland and William D. Marslen{-}Wilson and Li Su}, title = {On the similarities of representations in artificial and brain neural networks for speech recognition}, journal = {Frontiers Comput. Neurosci.}, volume = {16}, year = {2022}, url = {https://doi.org/10.3389/fncom.2022.1057439}, doi = {10.3389/FNCOM.2022.1057439}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ficn/WingfieldZDFTLWMS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/HuXCDLYGLM22, author = {Shoukang Hu and Xurong Xie and Mingyu Cui and Jiajun Deng and Shansong Liu and Jianwei Yu and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Neural Architecture Search for {LF-MMI} Trained Time Delay Neural Networks}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {30}, pages = {1093--1107}, year = {2022}, url = {https://doi.org/10.1109/TASLP.2022.3153253}, doi = {10.1109/TASLP.2022.3153253}, timestamp = {Fri, 01 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/HuXCDLYGLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/GengXYWLHLM22, author = {Mengzhe Geng and Xurong Xie and Zi Ye and Tianzi Wang and Guinan Li and Shujie Hu and Xunying Liu and Helen Meng}, title = {Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {30}, pages = {2597--2611}, year = {2022}, url = {https://doi.org/10.1109/TASLP.2022.3195113}, doi = {10.1109/TASLP.2022.3195113}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/GengXYWLHLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XueHXGLM22, author = {Boyang Xue and Shoukang Hu and Junhao Xu and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Bayesian Neural Network Language Modeling for Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {30}, pages = {2900--2917}, year = {2022}, url = {https://doi.org/10.1109/TASLP.2022.3203891}, doi = {10.1109/TASLP.2022.3203891}, timestamp = {Thu, 22 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/XueHXGLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiYDLM22, author = {Guinan Li and Jianwei Yu and Jiajun Deng and Xunying Liu and Helen Meng}, title = {Audio-Visual Multi-Channel Speech Separation, Dereverberation and Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6042--6046}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747237}, doi = {10.1109/ICASSP43922.2022.9747237}, timestamp = {Tue, 07 Jun 2022 17:34:47 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiYDLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangLWLSLM22, author = {Disong Wang and Songxiang Liu and Xixin Wu and Hui Lu and Lifa Sun and Xunying Liu and Helen Meng}, title = {Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6677--6681}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746680}, doi = {10.1109/ICASSP43922.2022.9746680}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangLWLSLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuLXGWHCLM22, author = {Shujie Hu and Shansong Liu and Xurong Xie and Mengzhe Geng and Tianzi Wang and Shoukang Hu and Mingyu Cui and Xunying Liu and Helen Meng}, title = {Exploiting Cross Domain Acoustic-to-Articulatory Inverted Features for Disordered Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6747--6751}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746989}, doi = {10.1109/ICASSP43922.2022.9746989}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HuLXGWHCLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WuHWLM22, author = {Xixin Wu and Shoukang Hu and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Neural Architecture Search for Speech Emotion Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {6902--6906}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746155}, doi = {10.1109/ICASSP43922.2022.9746155}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WuHWLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangYSLYM22, author = {Disong Wang and Shan Yang and Dan Su and Xunying Liu and Dong Yu and Helen Meng}, title = {{VCVTS:} Multi-Speaker Video-to-Speech Synthesis Via Cross-Modal Knowledge Transfer from Voice Conversion}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7252--7256}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747427}, doi = {10.1109/ICASSP43922.2022.9747427}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangYSLYM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuYLM22, author = {Junhao Xu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Mixed Precision {DNN} Quantization for Overlapped Speech Separation and Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7297--7301}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746885}, doi = {10.1109/ICASSP43922.2022.9746885}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XuYLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ZhengLYWSLM22, author = {Naijun Zheng and Na Li and Jianwei Yu and Chao Weng and Dan Su and Xunying Liu and Helen Meng}, title = {Multi-Channel Speaker Diarization Using Spatial Features for Meetings}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {7337--7341}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9747343}, doi = {10.1109/ICASSP43922.2022.9747343}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/ZhengLYWSLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SuZDLWLM22, author = {Hang Su and Danyang Zhao and Long Dang and Minglei Li and Xixin Wu and Xunying Liu and Helen Meng}, title = {A Multitask Learning Framework for Speaker Change Detection with Content Information from Unsupervised Speech Decomposition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2022, Virtual and Singapore, 23-27 May 2022}, pages = {8087--8091}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/ICASSP43922.2022.9746116}, doi = {10.1109/ICASSP43922.2022.9746116}, timestamp = {Tue, 07 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SuZDLWLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiWCLM22, author = {Jinchao Li and Shuai Wang and Yang Chao and Xunying Liu and Helen Meng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Context-aware Multimodal Fusion for Emotion Recognition}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2013--2017}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-10592}, doi = {10.21437/INTERSPEECH.2022-10592}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiWCLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XuHLM22, author = {Junhao Xu and Shoukang Hu and Xunying Liu and Helen Meng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Towards Green {ASR:} Lossless 4-bit Quantization of a Hybrid {TDNN} System on the 300-hr Swithboard Corpus}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2128--2132}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-678}, doi = {10.21437/INTERSPEECH.2022-678}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XuHLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DengXWCXJGLLM22, author = {Jiajun Deng and Xurong Xie and Tianzi Wang and Mingyu Cui and Boyang Xue and Zengrui Jin and Mengzhe Geng and Guinan Li and Xunying Liu and Helen Meng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Confidence Score Based Conformer Speaker Adaptation for Speech Recognition}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {2623--2627}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-680}, doi = {10.21437/INTERSPEECH.2022-680}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DengXWCXJGLLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/CuiDHXWHGXLM22, author = {Mingyu Cui and Jiajun Deng and Shoukang Hu and Xurong Xie and Tianzi Wang and Shujie Hu and Mengzhe Geng and Boyang Xue and Xunying Liu and Helen Meng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid {TDNN} {ASR} Systems}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {3158--3162}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-696}, doi = {10.21437/INTERSPEECH.2022-696}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/CuiDHXWHGXLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangWYMHWLM22, author = {Yi Wang and Tianzi Wang and Zi Ye and Lingwei Meng and Shoukang Hu and Xixin Wu and Xunying Liu and Helen Meng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Exploring linguistic feature and model combination for speech recognition based automatic {AD} detection}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {3328--3332}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-723}, doi = {10.21437/INTERSPEECH.2022-723}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangWYMHWLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangDGYHWCJLM22, author = {Tianzi Wang and Jiajun Deng and Mengzhe Geng and Zi Ye and Shoukang Hu and Yi Wang and Mingyu Cui and Zengrui Jin and Xunying Liu and Helen Meng}, editor = {Hanseok Ko and John H. L. Hansen}, title = {Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection}, booktitle = {Interspeech 2022, 23rd Annual Conference of the International Speech Communication Association, Incheon, Korea, 18-22 September 2022}, pages = {4825--4829}, publisher = {{ISCA}}, year = {2022}, url = {https://doi.org/10.21437/Interspeech.2022-712}, doi = {10.21437/INTERSPEECH.2022-712}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangDGYHWCJLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/LuWWWLM22, author = {Hui Lu and Disong Wang and Xixin Wu and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using {\ss}-VAE}, booktitle = {{IEEE} Spoken Language Technology Workshop, {SLT} 2022, Doha, Qatar, January 9-12, 2023}, pages = {814--821}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/SLT54892.2023.10022787}, doi = {10.1109/SLT54892.2023.10022787}, timestamp = {Mon, 06 Feb 2023 22:19:30 +0100}, biburl = {https://dblp.org/rec/conf/slt/LuWWWLM22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-03943, author = {Shoukang Hu and Xurong Xie and Mingyu Cui and Jiajun Deng and Shansong Liu and Jianwei Yu and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Neural Architecture Search For {LF-MMI} Trained Time Delay Neural Networks}, journal = {CoRR}, volume = {abs/2201.03943}, year = {2022}, url = {https://arxiv.org/abs/2201.03943}, eprinttype = {arXiv}, eprint = {2201.03943}, timestamp = {Fri, 21 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-03943.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-05554, author = {Mengzhe Geng and Shansong Liu and Jianwei Yu and Xurong Xie and Shoukang Hu and Zi Ye and Zengrui Jin and Xunying Liu and Helen Meng}, title = {Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition}, journal = {CoRR}, volume = {abs/2201.05554}, year = {2022}, url = {https://arxiv.org/abs/2201.05554}, eprinttype = {arXiv}, eprint = {2201.05554}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-05554.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-05562, author = {Mengzhe Geng and Xurong Xie and Shansong Liu and Jianwei Yu and Shoukang Hu and Xunying Liu and Helen Meng}, title = {Investigation of Data Augmentation Techniques for Disordered Speech Recognition}, journal = {CoRR}, volume = {abs/2201.05562}, year = {2022}, url = {https://arxiv.org/abs/2201.05562}, eprinttype = {arXiv}, eprint = {2201.05562}, timestamp = {Thu, 20 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-05562.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-05845, author = {Shansong Liu and Mengzhe Geng and Shoukang Hu and Xurong Xie and Mingyu Cui and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Recent Progress in the {CUHK} Dysarthric Speech Recognition System}, journal = {CoRR}, volume = {abs/2201.05845}, year = {2022}, url = {https://arxiv.org/abs/2201.05845}, eprinttype = {arXiv}, eprint = {2201.05845}, timestamp = {Fri, 21 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-05845.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-09422, author = {Xurong Xie and Rukiye Ruzi and Xunying Liu and Lan Wang}, title = {Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition}, journal = {CoRR}, volume = {abs/2201.09422}, year = {2022}, url = {https://arxiv.org/abs/2201.09422}, eprinttype = {arXiv}, eprint = {2201.09422}, timestamp = {Wed, 02 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-09422.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-09432, author = {Xurong Xie and Xiang Sui and Xunying Liu and Lan Wang}, title = {Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition}, journal = {CoRR}, volume = {abs/2201.09432}, year = {2022}, url = {https://arxiv.org/abs/2201.09432}, eprinttype = {arXiv}, eprint = {2201.09432}, timestamp = {Wed, 02 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-09432.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-09081, author = {Disong Wang and Shan Yang and Dan Su and Xunying Liu and Dong Yu and Helen Meng}, title = {{VCVTS:} Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion}, journal = {CoRR}, volume = {abs/2202.09081}, year = {2022}, url = {https://arxiv.org/abs/2202.09081}, eprinttype = {arXiv}, eprint = {2202.09081}, timestamp = {Thu, 03 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-09081.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-09082, author = {Disong Wang and Songxiang Liu and Xixin Wu and Hui Lu and Lifa Sun and Xunying Liu and Helen Meng}, title = {Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation}, journal = {CoRR}, volume = {abs/2202.09082}, year = {2022}, url = {https://arxiv.org/abs/2202.09082}, eprinttype = {arXiv}, eprint = {2202.09082}, timestamp = {Thu, 03 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-09082.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-10290, author = {Mengzhe Geng and Xurong Xie and Zi Ye and Tianzi Wang and Guinan Li and Shujie Hu and Xunying Liu and Helen Meng}, title = {Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition}, journal = {CoRR}, volume = {abs/2202.10290}, year = {2022}, url = {https://arxiv.org/abs/2202.10290}, eprinttype = {arXiv}, eprint = {2202.10290}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-10290.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-10274, author = {Shujie Hu and Shansong Liu and Xurong Xie and Mengzhe Geng and Tianzi Wang and Shoukang Hu and Mingyu Cui and Xunying Liu and Helen Meng}, title = {Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition}, journal = {CoRR}, volume = {abs/2203.10274}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.10274}, doi = {10.48550/ARXIV.2203.10274}, eprinttype = {arXiv}, eprint = {2203.10274}, timestamp = {Wed, 30 Mar 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-10274.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-14593, author = {Mengzhe Geng and Xurong Xie and Rongfeng Su and Jianwei Yu and Zi Ye and Xunying Liu and Helen Meng}, title = {On-the-fly Feature Based Speaker Adaptation for Dysarthric and Elderly Speech Recognition}, journal = {CoRR}, volume = {abs/2203.14593}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.14593}, doi = {10.48550/ARXIV.2203.14593}, eprinttype = {arXiv}, eprint = {2203.14593}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-14593.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-16928, author = {Xixin Wu and Shoukang Hu and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Neural Architecture Search for Speech Emotion Recognition}, journal = {CoRR}, volume = {abs/2203.16928}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.16928}, doi = {10.48550/ARXIV.2203.16928}, eprinttype = {arXiv}, eprint = {2203.16928}, timestamp = {Mon, 04 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-16928.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-01977, author = {Guinan Li and Jianwei Yu and Jiajun Deng and Xunying Liu and Helen Meng}, title = {Audio-visual multi-channel speech separation, dereverberation and recognition}, journal = {CoRR}, volume = {abs/2204.01977}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.01977}, doi = {10.48550/ARXIV.2204.01977}, eprinttype = {arXiv}, eprint = {2204.01977}, timestamp = {Wed, 06 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-01977.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2205-06445, author = {Zengrui Jin and Mengzhe Geng and Jiajun Deng and Tianzi Wang and Shujie Hu and Guinan Li and Xunying Liu}, title = {Personalized Adversarial Data Augmentation for Dysarthric and Elderly Speech Recognition}, journal = {CoRR}, volume = {abs/2205.06445}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2205.06445}, doi = {10.48550/ARXIV.2205.06445}, eprinttype = {arXiv}, eprint = {2205.06445}, timestamp = {Wed, 18 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2205-06445.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-07327, author = {Shujie Hu and Xurong Xie and Mengzhe Geng and Mingyu Cui and Jiajun Deng and Tianzi Wang and Xunying Liu and Helen Meng}, title = {Exploiting Cross-domain And Cross-Lingual Ultrasound Tongue Imaging Features For Elderly And Dysarthric Speech Recognition}, journal = {CoRR}, volume = {abs/2206.07327}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.07327}, doi = {10.48550/ARXIV.2206.07327}, eprinttype = {arXiv}, eprint = {2206.07327}, timestamp = {Mon, 20 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-07327.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-11596, author = {Mingyu Cui and Jiajun Deng and Shoukang Hu and Xurong Xie and Tianzi Wang and Shujie Hu and Mengzhe Geng and Boyang Xue and Xunying Liu and Helen Meng}, title = {Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid {TDNN} {ASR} Systems}, journal = {CoRR}, volume = {abs/2206.11596}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.11596}, doi = {10.48550/ARXIV.2206.11596}, eprinttype = {arXiv}, eprint = {2206.11596}, timestamp = {Tue, 28 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-11596.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-11643, author = {Junhao Xu and Shoukang Hu and Xunying Liu and Helen Meng}, title = {Towards Green {ASR:} Lossless 4-bit Quantization of a Hybrid {TDNN} System on the 300-hr Switchboard Corpus}, journal = {CoRR}, volume = {abs/2206.11643}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.11643}, doi = {10.48550/ARXIV.2206.11643}, eprinttype = {arXiv}, eprint = {2206.11643}, timestamp = {Mon, 27 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-11643.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-12045, author = {Jiajun Deng and Xurong Xie and Tianzi Wang and Mingyu Cui and Boyang Xue and Zengrui Jin and Mengzhe Geng and Guinan Li and Xunying Liu and Helen Meng}, title = {Confidence Score Based Conformer Speaker Adaptation for Speech Recognition}, journal = {CoRR}, volume = {abs/2206.12045}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.12045}, doi = {10.48550/ARXIV.2206.12045}, eprinttype = {arXiv}, eprint = {2206.12045}, timestamp = {Tue, 28 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-12045.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-13232, author = {Tianzi Wang and Jiajun Deng and Mengzhe Geng and Zi Ye and Shoukang Hu and Yi Wang and Mingyu Cui and Zengrui Jin and Xunying Liu and Helen Meng}, title = {Conformer Based Elderly Speech Recognition System for Alzheimer's Disease Detection}, journal = {CoRR}, volume = {abs/2206.13232}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.13232}, doi = {10.48550/ARXIV.2206.13232}, eprinttype = {arXiv}, eprint = {2206.13232}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-13232.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-13758, author = {Yi Wang and Tianzi Wang and Zi Ye and Lingwei Meng and Shoukang Hu and Xixin Wu and Xunying Liu and Helen Meng}, title = {Exploring linguistic feature and model combination for speech recognition based automatic {AD} detection}, journal = {CoRR}, volume = {abs/2206.13758}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.13758}, doi = {10.48550/ARXIV.2206.13758}, eprinttype = {arXiv}, eprint = {2206.13758}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-13758.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2208-13259, author = {Boyang Xue and Shoukang Hu and Junhao Xu and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Bayesian Neural Network Language Modeling for Speech Recognition}, journal = {CoRR}, volume = {abs/2208.13259}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2208.13259}, doi = {10.48550/ARXIV.2208.13259}, eprinttype = {arXiv}, eprint = {2208.13259}, timestamp = {Thu, 01 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2208-13259.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-13771, author = {Hui Lu and Disong Wang and Xixin Wu and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Disentangled Speech Representation Learning for One-Shot Cross-lingual Voice Conversion Using {\(\beta\)}-VAE}, journal = {CoRR}, volume = {abs/2210.13771}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.13771}, doi = {10.48550/ARXIV.2210.13771}, eprinttype = {arXiv}, eprint = {2210.13771}, timestamp = {Fri, 28 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-13771.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-16539, author = {Yi Wang and Jiajun Deng and Tianzi Wang and Bo Zheng and Shoukang Hu and Xunying Liu and Helen Meng}, title = {Exploiting prompt learning with pre-trained language models for Alzheimer's Disease detection}, journal = {CoRR}, volume = {abs/2210.16539}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.16539}, doi = {10.48550/ARXIV.2210.16539}, eprinttype = {arXiv}, eprint = {2210.16539}, timestamp = {Wed, 02 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-16539.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-01646, author = {Zengrui Jin and Xurong Xie and Mengzhe Geng and Tianzi Wang and Shujie Hu and Jiajun Deng and Guinan Li and Xunying Liu}, title = {Adversarial Data Augmentation Using {VAE-GAN} for Disordered Speech Recognition}, journal = {CoRR}, volume = {abs/2211.01646}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.01646}, doi = {10.48550/ARXIV.2211.01646}, eprinttype = {arXiv}, eprint = {2211.01646}, timestamp = {Fri, 04 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-01646.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-09313, author = {Xurong Xie and Xunying Liu and Hui Chen and Hongan Wang}, title = {Unsupervised Model-based speaker adaptation of end-to-end lattice-free {MMI} model for speech recognition}, journal = {CoRR}, volume = {abs/2211.09313}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.09313}, doi = {10.48550/ARXIV.2211.09313}, eprinttype = {arXiv}, eprint = {2211.09313}, timestamp = {Thu, 29 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-09313.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/WuCLLKWLM21, author = {Xixin Wu and Yuewen Cao and Hui Lu and Songxiang Liu and Shiyin Kang and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Exemplar-Based Emotive Speech Synthesis}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {874--886}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3052688}, doi = {10.1109/TASLP.2021.3052688}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/WuCLLKWLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/HuXLYYGLM21, author = {Shoukang Hu and Xurong Xie and Shansong Liu and Jianwei Yu and Zi Ye and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Bayesian Learning of {LF-MMI} Trained Time Delay Neural Networks for Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {1514--1529}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3069080}, doi = {10.1109/TASLP.2021.3069080}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/HuXLYYGLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/LiuCWWLM21, author = {Songxiang Liu and Yuewen Cao and Disong Wang and Xixin Wu and Xunying Liu and Helen Meng}, title = {Any-to-Many Voice Conversion With Location-Relative Sequence-to-Sequence Modeling}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {1717--1728}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3076867}, doi = {10.1109/TASLP.2021.3076867}, timestamp = {Tue, 15 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/LiuCWWLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/YuZWLHGLMY21, author = {Jianwei Yu and Shi{-}Xiong Zhang and Bo Wu and Shansong Liu and Shoukang Hu and Mengzhe Geng and Xunying Liu and Helen Meng and Dong Yu}, title = {Audio-Visual Multi-Channel Integration and Recognition of Overlapped Speech}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {2067--2082}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3078883}, doi = {10.1109/TASLP.2021.3078883}, timestamp = {Thu, 23 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/YuZWLHGLMY21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XieLLW21, author = {Xurong Xie and Xunying Liu and Tan Lee and Lan Wang}, title = {Bayesian Learning for Deep Neural Network Adaptation}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {2096--2110}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3084072}, doi = {10.1109/TASLP.2021.3084072}, timestamp = {Tue, 13 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/XieLLW21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/LiuGHXCYLM21, author = {Shansong Liu and Mengzhe Geng and Shoukang Hu and Xurong Xie and Mingyu Cui and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Recent Progress in the {CUHK} Dysarthric Speech Recognition System}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {2267--2281}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3091805}, doi = {10.1109/TASLP.2021.3091805}, timestamp = {Wed, 15 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/LiuGHXCYLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/WuCLLWWLM21, author = {Xixin Wu and Yuewen Cao and Hui Lu and Songxiang Liu and Disong Wang and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Speech Emotion Recognition Using Sequential Capsule Networks}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {3280--3291}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3120586}, doi = {10.1109/TASLP.2021.3120586}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/WuCLLWWLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/XuYHLM21, author = {Junhao Xu and Jianwei Yu and Shoukang Hu and Xunying Liu and Helen Meng}, title = {Mixed Precision Low-Bit Quantization of Neural Network Language Models for Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {29}, pages = {3679--3693}, year = {2021}, url = {https://doi.org/10.1109/TASLP.2021.3129357}, doi = {10.1109/TASLP.2021.3129357}, timestamp = {Sat, 25 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/XuYHLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/XieHWLSLL21, author = {Sirui Xie and Shoukang Hu and Xinjiang Wang and Chunxiao Liu and Jianping Shi and Xunying Liu and Dahua Lin}, editor = {Arindam Banerjee and Kenji Fukumizu}, title = {Understanding the wiring evolution in differentiable neural architecture search}, booktitle = {The 24th International Conference on Artificial Intelligence and Statistics, {AISTATS} 2021, April 13-15, 2021, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {130}, pages = {874--882}, publisher = {{PMLR}}, year = {2021}, url = {http://proceedings.mlr.press/v130/xie21a.html}, timestamp = {Wed, 14 Apr 2021 16:51:37 +0200}, biburl = {https://dblp.org/rec/conf/aistats/XieHWLSLL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangDZZYCLM21, author = {Disong Wang and Liqun Deng and Yang Zhang and Nianzu Zheng and Yu Ting Yeung and Xiao Chen and Xunying Liu and Helen Meng}, title = {Fcl-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech Synthesis}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {5714--5718}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414870}, doi = {10.1109/ICASSP39728.2021.9414870}, timestamp = {Tue, 11 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangDZZYCLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiLWL00M21, author = {Xu Li and Na Li and Chao Weng and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, title = {Replay and Synthetic Speech Detection with Res2Net Architecture}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6354--6358}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413828}, doi = {10.1109/ICASSP39728.2021.9413828}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiLWL00M21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiYYWMMLM21, author = {Jinchao Li and Jianwei Yu and Zi Ye and Simon Wong and Man{-}Wai Mak and Brian Mak and Xunying Liu and Helen Meng}, title = {A Comparative Study of Acoustic and Linguistic Features Classification for Alzheimer's Disease Detection}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6423--6427}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414147}, doi = {10.1109/ICASSP39728.2021.9414147}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiYYWMMLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/YeHLXGYXXLLM21, author = {Zi Ye and Shoukang Hu and Jinchao Li and Xurong Xie and Mengzhe Geng and Jianwei Yu and Junhao Xu and Boyang Xue and Shansong Liu and Xunying Liu and Helen Meng}, title = {Development of the Cuhk Elderly Speech Recognition System for Neurocognitive Disorder Detection Using the Dementiabank Corpus}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6433--6437}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413634}, doi = {10.1109/ICASSP39728.2021.9413634}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/YeHLXGYXXLLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ZhengLW0YWSLM21, author = {Naijun Zheng and Na Li and Bo Wu and Meng Yu and Jianwei Yu and Chao Weng and Dan Su and Xunying Liu and Helen Meng}, title = {A Joint Training Framework of Multi-Look Separator and Speaker Embedding Extractor for Overlapped Speech}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6698--6702}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414556}, doi = {10.1109/ICASSP39728.2021.9414556}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/ZhengLW0YWSLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuXLCGLM21, author = {Shoukang Hu and Xurong Xie and Shansong Liu and Mingyu Cui and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Neural Architecture Search for {LF-MMI} Trained Time Delay Neural Networks}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {6758--6762}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9413630}, doi = {10.1109/ICASSP39728.2021.9413630}, timestamp = {Fri, 09 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HuXLCGLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XueYXLHYGLM21, author = {Boyang Xue and Jianwei Yu and Junhao Xu and Shansong Liu and Shoukang Hu and Zi Ye and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Bayesian Transformer Language Models for Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {7378--7382}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414046}, doi = {10.1109/ICASSP39728.2021.9414046}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XueYXLHYGLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuHYLM21, author = {Junhao Xu and Shoukang Hu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Mixed Precision Quantization of Transformer Language Models for Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2021, Toronto, ON, Canada, June 6-11, 2021}, pages = {7383--7387}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICASSP39728.2021.9414076}, doi = {10.1109/ICASSP39728.2021.9414076}, timestamp = {Fri, 09 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XuHYLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangDYCLM21, author = {Disong Wang and Liqun Deng and Yu Ting Yeung and Xiao Chen and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {{VQMIVC:} Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-Shot Voice Conversion}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {1344--1348}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-283}, doi = {10.21437/INTERSPEECH.2021-283}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangDYCLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangDYCLM21a, author = {Disong Wang and Liqun Deng and Yu Ting Yeung and Xiao Chen and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {2956--2960}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-2139}, doi = {10.21437/INTERSPEECH.2021-2139}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangDYCLM21a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/Lu0WLKLM21, author = {Hui Lu and Zhiyong Wu and Xixin Wu and Xu Li and Shiyin Kang and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {{VAENAR-TTS:} Variational Auto-Encoder Based Non-AutoRegressive Text-to-Speech Synthesis}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {3775--3779}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-2121}, doi = {10.21437/INTERSPEECH.2021-2121}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/Lu0WLKLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiWLLM21, author = {Xu Li and Xixin Wu and Hui Lu and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Channel-Wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4314--4318}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-2125}, doi = {10.21437/INTERSPEECH.2021-2125}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiWLLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GengLYXHYJLM21, author = {Mengzhe Geng and Shansong Liu and Jianwei Yu and Xurong Xie and Shoukang Hu and Zi Ye and Zengrui Jin and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Spectro-Temporal Deep Features for Disordered Speech Assessment and Recognition}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4793--4797}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-60}, doi = {10.21437/INTERSPEECH.2021-60}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/GengLYXHYJLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/JinGXYLLM21, author = {Zengrui Jin and Mengzhe Geng and Xurong Xie and Jianwei Yu and Shansong Liu and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Adversarial Data Augmentation for Disordered Speech Recognition}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4803--4807}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-168}, doi = {10.21437/INTERSPEECH.2021-168}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/JinGXYLLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XieRLW21, author = {Xurong Xie and Rukiye Ruzi and Xunying Liu and Lan Wang}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4808--4812}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-173}, doi = {10.21437/INTERSPEECH.2021-173}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XieRLW21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WangLSWLM21, author = {Disong Wang and Songxiang Liu and Lifa Sun and Xixin Wu and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4813--4817}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-285}, doi = {10.21437/INTERSPEECH.2021-285}, timestamp = {Wed, 21 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WangLSWLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DengGHGXYLYLM21, author = {Jiajun Deng and Fabian Ritter Gutierrez and Shoukang Hu and Mengzhe Geng and Xurong Xie and Zi Ye and Shansong Liu and Jianwei Yu and Xunying Liu and Helen Meng}, editor = {Hynek Hermansky and Honza Cernock{\'{y}} and Luk{\'{a}}s Burget and Lori Lamel and Odette Scharenborg and Petr Motl{\'{\i}}cek}, title = {Bayesian Parametric and Architectural Domain Adaptation of {LF-MMI} Trained TDNNs for Elderly and Dysarthric Speech Recognition}, booktitle = {Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021}, pages = {4818--4822}, publisher = {{ISCA}}, year = {2021}, url = {https://doi.org/10.21437/Interspeech.2021-289}, doi = {10.21437/INTERSPEECH.2021-289}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DengGHGXYLYLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/CaoLKHLL00M21, author = {Yuewen Cao and Songxiang Liu and Shiyin Kang and Na Hu and Peng Liu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, title = {Exploring Cross-lingual Singing Voice Synthesis Using Speech Data}, 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/ISCSLP49672.2021.9362077}, doi = {10.1109/ISCSLP49672.2021.9362077}, timestamp = {Mon, 22 Mar 2021 16:16:13 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/CaoLKHLL00M21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/WangYWSLM21, author = {Disong Wang and Jianwei Yu and Xixin Wu and Lifa Sun and Xunying Liu and Helen Meng}, title = {Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initialization}, 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/ISCSLP49672.2021.9362068}, doi = {10.1109/ISCSLP49672.2021.9362068}, timestamp = {Mon, 22 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iscslp/WangYWSLM21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2102-04754, author = {Boyang Xue and Jianwei Yu and Junhao Xu and Shansong Liu and Shoukang Hu and Zi Ye and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Bayesian Transformer Language Models for Speech Recognition}, journal = {CoRR}, volume = {abs/2102.04754}, year = {2021}, url = {https://arxiv.org/abs/2102.04754}, eprinttype = {arXiv}, eprint = {2102.04754}, timestamp = {Thu, 07 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2102-04754.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2106-10127, author = {Disong Wang and Liqun Deng and Yu Ting Yeung and Xiao Chen and Xunying Liu and Helen Meng}, title = {Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization}, journal = {CoRR}, volume = {abs/2106.10127}, year = {2021}, url = {https://arxiv.org/abs/2106.10127}, eprinttype = {arXiv}, eprint = {2106.10127}, timestamp = {Tue, 11 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-10127.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2106-10132, author = {Disong Wang and Liqun Deng and Yu Ting Yeung and Xiao Chen and Xunying Liu and Helen Meng}, title = {{VQMIVC:} Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion}, journal = {CoRR}, volume = {abs/2106.10132}, year = {2021}, url = {https://arxiv.org/abs/2106.10132}, eprinttype = {arXiv}, eprint = {2106.10132}, timestamp = {Tue, 11 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-10132.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-03298, author = {Hui Lu and Zhiyong Wu and Xixin Wu and Xu Li and Shiyin Kang and Xunying Liu and Helen Meng}, title = {{VAENAR-TTS:} Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis}, journal = {CoRR}, volume = {abs/2107.03298}, year = {2021}, url = {https://arxiv.org/abs/2107.03298}, eprinttype = {arXiv}, eprint = {2107.03298}, timestamp = {Tue, 20 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-03298.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-08803, author = {Xu Li and Xixin Wu and Hui Lu and Xunying Liu and Helen Meng}, title = {Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks}, journal = {CoRR}, volume = {abs/2107.08803}, year = {2021}, url = {https://arxiv.org/abs/2107.08803}, eprinttype = {arXiv}, eprint = {2107.08803}, timestamp = {Thu, 22 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-08803.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2108-00899, author = {Zengrui Jin and Mengzhe Geng and Xurong Xie and Jianwei Yu and Shansong Liu and Xunying Liu and Helen Meng}, title = {Adversarial Data Augmentation for Disordered Speech Recognition}, journal = {CoRR}, volume = {abs/2108.00899}, year = {2021}, url = {https://arxiv.org/abs/2108.00899}, eprinttype = {arXiv}, eprint = {2108.00899}, timestamp = {Thu, 05 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2108-00899.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2111-14479, author = {Junhao Xu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Mixed Precision {DNN} Qunatization for Overlapped Speech Separation and Recognition}, journal = {CoRR}, volume = {abs/2111.14479}, year = {2021}, url = {https://arxiv.org/abs/2111.14479}, eprinttype = {arXiv}, eprint = {2111.14479}, timestamp = {Wed, 01 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-14479.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2111-14836, author = {Junhao Xu and Xie Chen and Shoukang Hu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers}, journal = {CoRR}, volume = {abs/2111.14836}, year = {2021}, url = {https://arxiv.org/abs/2111.14836}, eprinttype = {arXiv}, eprint = {2111.14836}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-14836.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2112-11438, author = {Junhao Xu and Jianwei Yu and Shoukang Hu and Xunying Liu and Helen Meng}, title = {Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition}, journal = {CoRR}, volume = {abs/2112.11438}, year = {2021}, url = {https://arxiv.org/abs/2112.11438}, eprinttype = {arXiv}, eprint = {2112.11438}, timestamp = {Tue, 04 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2112-11438.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2112-11540, author = {Junhao Xu and Shoukang Hu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Mixed Precision of Quantization of Transformer Language Models for Speech Recognition}, journal = {CoRR}, volume = {abs/2112.11540}, year = {2021}, url = {https://arxiv.org/abs/2112.11540}, eprinttype = {arXiv}, eprint = {2112.11540}, timestamp = {Tue, 04 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2112-11540.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/SuLWY20, author = {Rongfeng Su and Xunying Liu and Lan Wang and Jingzhou Yang}, title = {Cross-Domain Deep Visual Feature Generation for Mandarin Audio-Visual Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {28}, pages = {185--197}, year = {2020}, url = {https://doi.org/10.1109/TASLP.2019.2950602}, doi = {10.1109/TASLP.2019.2950602}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/SuLWY20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cvpr/HuXZLSLL20, author = {Shoukang Hu and Sirui Xie and Hehui Zheng and Chunxiao Liu and Jianping Shi and Xunying Liu and Dahua Lin}, title = {{DSNAS:} Direct Neural Architecture Search Without Parameter Retraining}, booktitle = {2020 {IEEE/CVF} Conference on Computer Vision and Pattern Recognition, {CVPR} 2020, Seattle, WA, USA, June 13-19, 2020}, pages = {12081--12089}, publisher = {Computer Vision Foundation / {IEEE}}, year = {2020}, url = {https://openaccess.thecvf.com/content\_CVPR\_2020/html/Hu\_DSNAS\_Direct\_Neural\_Architecture\_Search\_Without\_Parameter\_Retraining\_CVPR\_2020\_paper.html}, doi = {10.1109/CVPR42600.2020.01210}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/cvpr/HuXZLSLL20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuWCSWKWLSYM20, author = {Songxiang Liu and Disong Wang and Yuewen Cao and Lifa Sun and Xixin Wu and Shiyin Kang and Zhiyong Wu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, title = {End-To-End Accent Conversion Without Using Native Utterances}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {6289--6293}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053797}, doi = {10.1109/ICASSP40776.2020.9053797}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuWCSWKWLSYM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiZWYLM20, author = {Xu Li and Jinghua Zhong and Xixin Wu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Adversarial Attacks on {GMM} I-Vector Based Speaker Verification Systems}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {6579--6583}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053076}, doi = {10.1109/ICASSP40776.2020.9053076}, timestamp = {Thu, 23 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiZWYLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/YuZWGWKLLMY20, author = {Jianwei Yu and Shi{-}Xiong Zhang and Jian Wu and Shahram Ghorbani and Bo Wu and Shiyin Kang and Shansong Liu and Xunying Liu and Helen Meng and Dong Yu}, title = {Audio-Visual Recognition of Overlapped Speech for the {LRS2} Dataset}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {6984--6988}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9054127}, doi = {10.1109/ICASSP40776.2020.9054127}, timestamp = {Tue, 17 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/YuZWGWKLLMY20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/CaoLWKLWLSYM20, author = {Yuewen Cao and Songxiang Liu and Xixin Wu and Shiyin Kang and Peng Liu and Zhiyong Wu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, title = {Code-Switched Speech Synthesis Using Bilingual Phonetic Posteriorgram with Only Monolingual Corpora}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {7619--7623}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053094}, doi = {10.1109/ICASSP40776.2020.9053094}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/CaoLWKLWLSYM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangYWLSLM20, author = {Disong Wang and Jianwei Yu and Xixin Wu and Songxiang Liu and Lifa Sun and Xunying Liu and Helen Meng}, title = {End-To-End Voice Conversion Via Cross-Modal Knowledge Distillation for Dysarthric Speech Reconstruction}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {7744--7748}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9054596}, doi = {10.1109/ICASSP40776.2020.9054596}, timestamp = {Thu, 23 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangYWLSLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XuCHYLM20, author = {Junhao Xu and Xie Chen and Shoukang Hu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Low-bit Quantization of Recurrent Neural Network Language Models Using Alternating Direction Methods of Multipliers}, booktitle = {2020 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2020, Barcelona, Spain, May 4-8, 2020}, pages = {7939--7943}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICASSP40776.2020.9053483}, doi = {10.1109/ICASSP40776.2020.9053483}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/XuCHYLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/GengXLYHLM20, author = {Mengzhe Geng and Xurong Xie and Shansong Liu and Jianwei Yu and Shoukang Hu and Xunying Liu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Investigation of Data Augmentation Techniques for Disordered Speech Recognition}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {696--700}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-1161}, doi = {10.21437/INTERSPEECH.2020-1161}, timestamp = {Fri, 29 Jan 2021 17:40:16 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/GengXLYHLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuXYHGSZLM20, author = {Shansong Liu and Xurong Xie and Jianwei Yu and Shoukang Hu and Mengzhe Geng and Rongfeng Su and Shi{-}Xiong Zhang and Xunying Liu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Exploiting Cross-Domain Visual Feature Generation for Disordered Speech Recognition}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {711--715}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2282}, doi = {10.21437/INTERSPEECH.2020-2282}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LiuXYHGSZLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiLZWLSYM20, author = {Xu Li and Na Li and Jinghua Zhong and Xixin Wu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {1540--1544}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2441}, doi = {10.21437/INTERSPEECH.2020-2441}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiLZWLSYM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ZhengWZLM20, author = {Naijun Zheng and Xixin Wu and Jinghua Zhong and Xunying Liu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Speaker-Aware Linear Discriminant Analysis in Speaker Verification}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {3012--3016}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2061}, doi = {10.21437/INTERSPEECH.2020-2061}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/ZhengWZLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/YuWGZCX00YLM20, author = {Jianwei Yu and Bo Wu and Rongzhi Gu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Dong Yu and Xunying Liu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Audio-Visual Multi-Channel Recognition of Overlapped Speech}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {3496--3500}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2346}, doi = {10.21437/INTERSPEECH.2020-2346}, timestamp = {Fri, 05 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/YuWGZCX00YLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuCKHL00M20, author = {Songxiang Liu and Yuewen Cao and Shiyin Kang and Na Hu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, editor = {Helen Meng and Bo Xu and Thomas Fang Zheng}, title = {Transferring Source Style in Non-Parallel Voice Conversion}, booktitle = {Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25-29 October 2020}, pages = {4721--4725}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Interspeech.2020-2412}, doi = {10.21437/INTERSPEECH.2020-2412}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LiuCKHL00M20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/odyssey/LiZYHWLM20, author = {Xu Li and Jinghua Zhong and Jianwei Yu and Shoukang Hu and Xixin Wu and Xunying Liu and Helen Meng}, editor = {Kong{-}Aik Lee and Takafumi Koshinaka and Koichi Shinoda}, title = {Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification}, booktitle = {Odyssey 2020: The Speaker and Language Recognition Workshop, 1-5 November 2020, Tokyo, Japan}, pages = {365--371}, publisher = {{ISCA}}, year = {2020}, url = {https://doi.org/10.21437/Odyssey.2020-51}, doi = {10.21437/ODYSSEY.2020-51}, timestamp = {Tue, 16 Nov 2021 11:36:03 +0100}, biburl = {https://dblp.org/rec/conf/odyssey/LiZYHWLM20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-01656, author = {Jianwei Yu and Shi{-}Xiong Zhang and Jian Wu and Shahram Ghorbani and Bo Wu and Shiyin Kang and Shansong Liu and Xunying Liu and Helen Meng and Dong Yu}, title = {Audio-visual Recognition of Overlapped speech for the {LRS2} dataset}, journal = {CoRR}, volume = {abs/2001.01656}, year = {2020}, url = {http://arxiv.org/abs/2001.01656}, eprinttype = {arXiv}, eprint = {2001.01656}, timestamp = {Tue, 17 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-01656.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-00205, author = {Xu Li and Xixin Wu and Xunying Liu and Helen Meng}, title = {Deep segmental phonetic posterior-grams based discovery of non-categories in {L2} English speech}, journal = {CoRR}, volume = {abs/2002.00205}, year = {2020}, url = {https://arxiv.org/abs/2002.00205}, eprinttype = {arXiv}, eprint = {2002.00205}, timestamp = {Mon, 10 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-00205.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-09128, author = {Shoukang Hu and Sirui Xie and Hehui Zheng and Chunxiao Liu and Jianping Shi and Xunying Liu and Dahua Lin}, title = {{DSNAS:} Direct Neural Architecture Search without Parameter Retraining}, journal = {CoRR}, volume = {abs/2002.09128}, year = {2020}, url = {https://arxiv.org/abs/2002.09128}, eprinttype = {arXiv}, eprint = {2002.09128}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-09128.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2004-04014, author = {Xu Li and Jinghua Zhong and Jianwei Yu and Shoukang Hu and Xixin Wu and Xunying Liu and Helen Meng}, title = {Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification}, journal = {CoRR}, volume = {abs/2004.04014}, year = {2020}, url = {https://arxiv.org/abs/2004.04014}, eprinttype = {arXiv}, eprint = {2004.04014}, timestamp = {Wed, 15 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2004-04014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-08571, author = {Jianwei Yu and Bo Wu and Rongzhi Gu and Shi{-}Xiong Zhang and Lianwu Chen and Yong Xu and Meng Yu and Dan Su and Dong Yu and Xunying Liu and Helen Meng}, title = {Audio-visual Multi-channel Recognition of Overlapped Speech}, journal = {CoRR}, volume = {abs/2005.08571}, year = {2020}, url = {https://arxiv.org/abs/2005.08571}, eprinttype = {arXiv}, eprint = {2005.08571}, timestamp = {Fri, 30 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-08571.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-06186, author = {Xu Li and Na Li and Jinghua Zhong and Xixin Wu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, title = {Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification}, journal = {CoRR}, volume = {abs/2006.06186}, year = {2020}, url = {https://arxiv.org/abs/2006.06186}, eprinttype = {arXiv}, eprint = {2006.06186}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-06186.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2007-08818, author = {Shoukang Hu and Xurong Xie and Shansong Liu and Mengzhe Geng and Xunying Liu and Helen Meng}, title = {Neural Architecture Search for Speech Recognition}, journal = {CoRR}, volume = {abs/2007.08818}, year = {2020}, url = {https://arxiv.org/abs/2007.08818}, eprinttype = {arXiv}, eprint = {2007.08818}, timestamp = {Wed, 29 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2007-08818.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2009-01272, author = {Sirui Xie and Shoukang Hu and Xinjiang Wang and Chunxiao Liu and Jianping Shi and Xunying Liu and Dahua Lin}, title = {Understanding the wiring evolution in differentiable neural architecture search}, journal = {CoRR}, volume = {abs/2009.01272}, year = {2020}, url = {https://arxiv.org/abs/2009.01272}, eprinttype = {arXiv}, eprint = {2009.01272}, timestamp = {Wed, 16 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2009-01272.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2009-02725, author = {Songxiang Liu and Yuewen Cao and Disong Wang and Xixin Wu and Xunying Liu and Helen Meng}, title = {Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling}, journal = {CoRR}, volume = {abs/2009.02725}, year = {2020}, url = {https://arxiv.org/abs/2009.02725}, eprinttype = {arXiv}, eprint = {2009.02725}, timestamp = {Fri, 18 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2009-02725.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-15006, author = {Xu Li and Na Li and Chao Weng and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, title = {Replay and Synthetic Speech Detection with Res2net Architecture}, journal = {CoRR}, volume = {abs/2010.15006}, year = {2020}, url = {https://arxiv.org/abs/2010.15006}, eprinttype = {arXiv}, eprint = {2010.15006}, timestamp = {Thu, 11 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-15006.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-01678, author = {Disong Wang and Songxiang Liu and Lifa Sun and Xixin Wu and Xunying Liu and Helen Meng}, title = {Learning Explicit Prosody Models and Deep Speaker Embeddings for Atypical Voice Conversion}, journal = {CoRR}, volume = {abs/2011.01678}, year = {2020}, url = {https://arxiv.org/abs/2011.01678}, eprinttype = {arXiv}, eprint = {2011.01678}, timestamp = {Fri, 10 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-01678.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-07460, author = {Xurong Xie and Xunying Liu and Tan Lee and Lan Wang}, title = {Bayesian Learning for Deep Neural Network Adaptation}, journal = {CoRR}, volume = {abs/2012.07460}, year = {2020}, url = {https://arxiv.org/abs/2012.07460}, eprinttype = {arXiv}, eprint = {2012.07460}, timestamp = {Sat, 02 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-07460.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/ChenLWRWG19, author = {Xie Chen and Xunying Liu and Yu Wang and Anton Ragni and Jeremy Heng Meng Wong and Mark J. F. Gales}, title = {Exploiting Future Word Contexts in Neural Network Language Models for Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {27}, number = {9}, pages = {1444--1454}, year = {2019}, url = {https://doi.org/10.1109/TASLP.2019.2922048}, doi = {10.1109/TASLP.2019.2922048}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/ChenLWRWG19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/XieLLHW19, author = {Xurong Xie and Xunying Liu and Tan Lee and Shoukang Hu and Lan Wang}, title = {{BLHUC:} Bayesian Learning of Hidden Unit Contributions for Deep Neural Network Speaker Adaptation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {5711--5715}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682667}, doi = {10.1109/ICASSP.2019.8682667}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/XieLLHW19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/HuLXLYWLM19, author = {Shoukang Hu and Max W. Y. Lam and Xurong Xie and Shansong Liu and Jianwei Yu and Xixin Wu and Xunying Liu and Helen Meng}, title = {Bayesian and Gaussian Process Neural Networks for Large Vocabulary Continuous Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {6555--6559}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682487}, doi = {10.1109/ICASSP.2019.8682487}, timestamp = {Sun, 30 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/HuLXLYWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WuLCLYDMHWLM19, author = {Xixin Wu and Songxiang Liu and Yuewen Cao and Xu Li and Jianwei Yu and Dongyang Dai and Xi Ma and Shoukang Hu and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Speech Emotion Recognition Using Capsule Networks}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {6695--6699}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8683163}, doi = {10.1109/ICASSP.2019.8683163}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WuLCLYDMHWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/CaoWLYLWLM19, author = {Yuewen Cao and Xixin Wu and Songxiang Liu and Jianwei Yu and Xu Li and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {End-to-end Code-switched {TTS} with Mix of Monolingual Recordings}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {6935--6939}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682927}, doi = {10.1109/ICASSP.2019.8682927}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/CaoWLYLWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LamCHYLM19, author = {Max W. Y. Lam and Xie Chen and Shoukang Hu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Gaussian Process Lstm Recurrent Neural Network Language Models for Speech Recognition}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {7235--7239}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8683660}, doi = {10.1109/ICASSP.2019.8683660}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LamCHYLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/YuLCHLWLM19, author = {Jianwei Yu and Max W. Y. Lam and Xie Chen and Shoukang Hu and Songxiang Liu and Xixin Wu and Xunying Liu and Helen Meng}, title = {Recurrent Neural Network Language Model Training Using Natural Gradient}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {7260--7264}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682445}, doi = {10.1109/ICASSP.2019.8682445}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/YuLCHLWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LeungLM19, author = {Wai{-}Kim Leung and Xunying Liu and Helen Meng}, title = {{CNN-RNN-CTC} Based End-to-end Mispronunciation Detection and Diagnosis}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2019, Brighton, United Kingdom, May 12-17, 2019}, pages = {8132--8136}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/ICASSP.2019.8682654}, doi = {10.1109/ICASSP.2019.8682654}, timestamp = {Sun, 30 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LeungLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuCWSLM19, author = {Songxiang Liu and Yuewen Cao and Xixin Wu and Lifa Sun and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Jointly Trained Conversion Model and WaveNet Vocoder for Non-Parallel Voice Conversion Using Mel-Spectrograms and Phonetic Posteriorgrams}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {714--718}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1316}, doi = {10.21437/INTERSPEECH.2019-1316}, timestamp = {Fri, 29 Jan 2021 17:41:10 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LiuCWSLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XieLLW19, author = {Xurong Xie and Xunying Liu and Tan Lee and Lan Wang}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Fast {DNN} Acoustic Model Speaker Adaptation by Learning Hidden Unit Contribution Features}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {759--763}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-2050}, doi = {10.21437/INTERSPEECH.2019-2050}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/XieLLW19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LamWLMSY19, author = {Max W. Y. Lam and Jun Wang and Xunying Liu and Helen Meng and Dan Su and Dong Yu}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Extract, Adapt and Recognize: An End-to-End Neural Network for Corrupted Monaural Speech Recognition}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {2778--2782}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1626}, doi = {10.21437/INTERSPEECH.2019-1626}, timestamp = {Wed, 22 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LamWLMSY19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HuXLLYWLM19, author = {Shoukang Hu and Xurong Xie and Shansong Liu and Max W. Y. Lam and Jianwei Yu and Xixin Wu and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {{LF-MMI} Training of Bayesian and Gaussian Process Time Delay Neural Networks for Speech Recognition}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {2793--2797}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-2379}, doi = {10.21437/INTERSPEECH.2019-2379}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/HuXLLYWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SuDWLM19, author = {Hang Su and Borislav Dzodzo and Xixin Wu and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Unsupervised Methods for Audio Classification from Lecture Discussion Recordings}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {3347--3351}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-2384}, doi = {10.21437/INTERSPEECH.2019-2384}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/SuDWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/YuLHWLCLM19, author = {Jianwei Yu and Max W. Y. Lam and Shoukang Hu and Xixin Wu and Xu Li and Yuewen Cao and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Comparative Study of Parametric and Representation Uncertainty Modeling for Recurrent Neural Network Language Models}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {3510--3514}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1927}, doi = {10.21437/INTERSPEECH.2019-1927}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/YuLHWLCLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HuLCGCCHYWLM19, author = {Shoukang Hu and Shansong Liu and Heng Fai Chang and Mengzhe Geng and Jiani Chen and Lau Wing Chung and To Ka Hei and Jianwei Yu and Ka Ho Wong and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {The {CUHK} Dysarthric Speech Recognition Systems for English and Cantonese}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {3669--3670}, publisher = {{ISCA}}, year = {2019}, url = {https://www.isca-speech.org/archive/interspeech\_2019/hu19c\_interspeech.html}, timestamp = {Tue, 27 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HuLCGCCHYWLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuHWYSLM19, author = {Shansong Liu and Shoukang Hu and Yi Wang and Jianwei Yu and Rongfeng Su and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {Exploiting Visual Features Using Bayesian Gated Neural Networks for Disordered Speech Recognition}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {4120--4124}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-1536}, doi = {10.21437/INTERSPEECH.2019-1536}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LiuHWYSLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuHLM19, author = {Shansong Liu and Shoukang Hu and Xunying Liu and Helen Meng}, editor = {Gernot Kubin and Zdravko Kacic}, title = {On the Use of Pitch Features for Disordered Speech Recognition}, booktitle = {Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019}, pages = {4130--4134}, publisher = {{ISCA}}, year = {2019}, url = {https://doi.org/10.21437/Interspeech.2019-2609}, doi = {10.21437/INTERSPEECH.2019-2609}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LiuHLM19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-03078, author = {Xu Li and Jinghua Zhong and Xixin Wu and Jianwei Yu and Xunying Liu and Helen Meng}, title = {Adversarial Attacks on {GMM} i-vector based Speaker Verification Systems}, journal = {CoRR}, volume = {abs/1911.03078}, year = {2019}, url = {http://arxiv.org/abs/1911.03078}, eprinttype = {arXiv}, eprint = {1911.03078}, timestamp = {Mon, 11 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-03078.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hicss/LamLMT18, author = {Max W. Y. Lam and Xunying Liu and Helen Mei{-}Ling Meng and Kelvin Kam{-}fai Tsoi}, editor = {Tung Bui}, title = {Drawing-Based Automatic Dementia Screening Using Gaussian Process Markov Chains}, booktitle = {51st Hawaii International Conference on System Sciences, {HICSS} 2018, Hilton Waikoloa Village, Hawaii, USA, January 3-6, 2018}, pages = {1--10}, publisher = {ScholarSpace / {AIS} Electronic Library (AISeL)}, year = {2018}, url = {https://hdl.handle.net/10125/50241}, timestamp = {Wed, 04 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hicss/LamLMT18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WuSKLWLM18, author = {Xixin Wu and Lifa Sun and Shiyin Kang and Songxiang Liu and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Feature Based Adaptation for Speaking Style Synthesis}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {5304--5308}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8462178}, doi = {10.1109/ICASSP.2018.8462178}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WuSKLWLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuLSYXCM18, author = {Xunying Liu and Shansong Liu and Jinze Sha and Jianwei Yu and Zhiyuan Xu and Xie Chen and Helen Meng}, title = {Limited-Memory {BFGS} Optimization of Recurrent Neural Network Language Models for Speech Recognition}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {6114--6118}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8461550}, doi = {10.1109/ICASSP.2018.8461550}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiuLSYXCM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/MaoLLWLM18, author = {Shaoguang Mao and Xu Li and Kun Li and Zhiyong Wu and Xunying Liu and Helen Meng}, title = {Unsupervised Discovery of an Extended Phoneme Set in {L2} English Speech for Mispronunciation Detection and Diagnosis}, booktitle = {2018 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2018, Calgary, AB, Canada, April 15-20, 2018}, pages = {6244--6248}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICASSP.2018.8462635}, doi = {10.1109/ICASSP.2018.8462635}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/MaoLLWLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuZSWLM18, author = {Songxiang Liu and Jinghua Zhong and Lifa Sun and Xixin Wu and Xunying Liu and Helen Meng}, editor = {B. Yegnanarayana}, title = {Voice Conversion Across Arbitrary Speakers Based on a Single Target-Speaker Utterance}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {496--500}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1504}, doi = {10.21437/INTERSPEECH.2018-1504}, timestamp = {Fri, 21 May 2021 08:16:43 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuZSWLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LamHXLYSLM18, author = {Max W. Y. Lam and Shoukang Hu and Xurong Xie and Shansong Liu and Jianwei Yu and Rongfeng Su and Xunying Liu and Helen Meng}, editor = {B. Yegnanarayana}, title = {Gaussian Process Neural Networks for Speech Recognition}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {1778--1782}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1823}, doi = {10.21437/INTERSPEECH.2018-1823}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LamHXLYSLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiMWLLM18, author = {Xu Li and Shaoguang Mao and Xixin Wu and Kun Li and Xunying Liu and Helen Meng}, editor = {B. Yegnanarayana}, title = {Unsupervised Discovery of Non-native Phonetic Patterns in {L2} English Speech for Mispronunciation Detection and Diagnosis}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {2554--2558}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-2027}, doi = {10.21437/INTERSPEECH.2018-2027}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LiMWLLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/YuXLHLWWLM18, author = {Jianwei Yu and Xurong Xie and Shansong Liu and Shoukang Hu and Max W. Y. Lam and Xixin Wu and Ka Ho Wong and Xunying Liu and Helen Meng}, editor = {B. Yegnanarayana}, title = {Development of the {CUHK} Dysarthric Speech Recognition System for the {UA} Speech Corpus}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {2938--2942}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1541}, doi = {10.21437/INTERSPEECH.2018-1541}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/YuXLHLWWLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/WuCWLKWLSYM18, author = {Xixin Wu and Yuewen Cao and Mu Wang and Songxiang Liu and Shiyin Kang and Zhiyong Wu and Xunying Liu and Dan Su and Dong Yu and Helen Meng}, editor = {B. Yegnanarayana}, title = {Rapid Style Adaptation Using Residual Error Embedding for Expressive Speech Synthesis}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {3072--3076}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1991}, doi = {10.21437/INTERSPEECH.2018-1991}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/WuCWLKWLSYM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SuLW18, author = {Rongfeng Su and Xunying Liu and Lan Wang}, editor = {B. Yegnanarayana}, title = {Semi-supervised Cross-domain Visual Feature Learning for Audio-Visual Broadcast Speech Transcription}, booktitle = {Interspeech 2018, 19th Annual Conference of the International Speech Communication Association, Hyderabad, India, 2-6 September 2018}, pages = {3509--3513}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Interspeech.2018-1063}, doi = {10.21437/INTERSPEECH.2018-1063}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/SuLW18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/XieLLW18, author = {Xurong Xie and Xunying Liu and Tan Lee and Lan Wang}, title = {Investigation of Stacked Deep Neural Networks and Mixture Density Networks for Acoustic-to-Articulatory Inversion}, booktitle = {11th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2018, Taipei City, Taiwan, November 26-29, 2018}, pages = {36--40}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ISCSLP.2018.8706709}, doi = {10.1109/ISCSLP.2018.8706709}, timestamp = {Wed, 16 Oct 2019 14:14:48 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/XieLLW18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/odyssey/LiuSWLM18, author = {Songxiang Liu and Lifa Sun and Xixin Wu and Xunying Liu and Helen Meng}, editor = {Anthony Larcher and Jean{-}Fran{\c{c}}ois Bonastre}, title = {The {HCCL-CUHK} System for the Voice Conversion Challenge 2018}, booktitle = {Odyssey 2018: The Speaker and Language Recognition Workshop, 26-29 June 2018, Les Sables d'Olonne, France}, pages = {248--254}, publisher = {{ISCA}}, year = {2018}, url = {https://doi.org/10.21437/Odyssey.2018-35}, doi = {10.21437/ODYSSEY.2018-35}, timestamp = {Tue, 16 Nov 2021 11:36:04 +0100}, biburl = {https://dblp.org/rec/conf/odyssey/LiuSWLM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ploscb/WingfieldSLZWTF17, author = {Cai Wingfield and Li Su and Xunying Liu and Chao Zhang and Philip C. Woodland and Andrew Thwaites and Elisabeth Fonteneau and William D. Marslen{-}Wilson}, title = {Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem}, journal = {PLoS Comput. Biol.}, volume = {13}, number = {9}, year = {2017}, url = {https://doi.org/10.1371/journal.pcbi.1005617}, doi = {10.1371/JOURNAL.PCBI.1005617}, timestamp = {Thu, 25 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ploscb/WingfieldSLZWTF17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ialp/SuWL17, author = {Rongfeng Su and Lan Wang and Xunying Liu}, editor = {Rong Tong and Yue Zhang and Yanfeng Lu and Minghui Dong}, title = {Multimodal learning using 3D audio-visual data for audio-visual speech recognition}, booktitle = {2017 International Conference on Asian Language Processing, {IALP} 2017, Singapore, December 5-7, 2017}, pages = {40--43}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IALP.2017.8300541}, doi = {10.1109/IALP.2017.8300541}, timestamp = {Mon, 27 Apr 2020 16:36:09 +0200}, biburl = {https://dblp.org/rec/conf/ialp/SuWL17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiWLMC17, author = {Runnan Li and Zhiyong Wu and Xunying Liu and Helen M. Meng and Lianhong Cai}, title = {Multi-task learning of structured output layer bidirectional {LSTMS} for speech synthesis}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {5510--5514}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7953210}, doi = {10.1109/ICASSP.2017.7953210}, timestamp = {Sat, 08 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiWLMC17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenRVLKG17, author = {Xie Chen and Anton Ragni and J. Vasilakes and Xunying Liu and Kate Knill and Mark J. F. Gales}, title = {Recurrent neural network language models for keyword search}, booktitle = {2017 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2017, New Orleans, LA, USA, March 5-9, 2017}, pages = {5775--5779}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICASSP.2017.7953263}, doi = {10.1109/ICASSP.2017.7953263}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/ChenRVLKG17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChenRLG17, author = {Xie Chen and Anton Ragni and Xunying Liu and Mark J. F. Gales}, editor = {Francisco Lacerda}, title = {Investigating Bidirectional Recurrent Neural Network Language Models for Speech Recognition}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {269--273}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-513}, doi = {10.21437/INTERSPEECH.2017-513}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChenRLG17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XieLLW17, author = {Xurong Xie and Xunying Liu and Tan Lee and Lan Wang}, editor = {Francisco Lacerda}, title = {{RNN-LDA} Clustering for Feature Based {DNN} Adaptation}, booktitle = {Interspeech 2017, 18th Annual Conference of the International Speech Communication Association, Stockholm, Sweden, August 20-24, 2017}, pages = {2396--2400}, publisher = {{ISCA}}, year = {2017}, url = {https://doi.org/10.21437/Interspeech.2017-368}, doi = {10.21437/INTERSPEECH.2017-368}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XieLLW17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1708-05592, author = {Xie Chen and Xunying Liu and Anton Ragni and Yu Wang and Mark J. F. Gales}, title = {Future Word Contexts in Neural Network Language Models}, journal = {CoRR}, volume = {abs/1708.05592}, year = {2017}, url = {http://arxiv.org/abs/1708.05592}, eprinttype = {arXiv}, eprint = {1708.05592}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1708-05592.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/LiuCWGW16, author = {Xunying Liu and Xie Chen and Yongqiang Wang and Mark J. F. Gales and Philip C. Woodland}, title = {Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {24}, number = {8}, pages = {1438--1449}, year = {2016}, url = {https://doi.org/10.1109/TASLP.2016.2558826}, doi = {10.1109/TASLP.2016.2558826}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/LiuCWGW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/ChenLWGW16, author = {Xie Chen and Xunying Liu and Yongqiang Wang and Mark J. F. Gales and Philip C. Woodland}, title = {Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {24}, number = {11}, pages = {2146--2157}, year = {2016}, url = {https://doi.org/10.1109/TASLP.2016.2598304}, doi = {10.1109/TASLP.2016.2598304}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/ChenLWGW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/WangZWGKLLQ16, author = {Linlin Wang and Chao Zhang and Philip C. Woodland and Mark J. F. Gales and Panagiota Karanasou and Pierre Lanchantin and Xunying Liu and Yanmin Qian}, title = {Improved DNN-based segmentation for multi-genre broadcast audio}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {5700--5704}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472769}, doi = {10.1109/ICASSP.2016.7472769}, timestamp = {Tue, 23 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/WangZWGKLLQ16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenLQGW16, author = {Xie Chen and Xunying Liu and Y. Qian and Mark J. F. Gales and Philip C. Woodland}, title = {{CUED-RNNLM} - An open-source toolkit for efficient training and evaluation of recurrent neural network language models}, booktitle = {2016 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2016, Shanghai, China, March 20-25, 2016}, pages = {6000--6004}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICASSP.2016.7472829}, doi = {10.1109/ICASSP.2016.7472829}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/ChenLQGW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icinfa/SuLW16, author = {Rongfeng Su and Xunying Liu and Lan Wang}, title = {Convolutional neural network bottleneck features for bi-directional generalized variable parameter HMMs}, booktitle = {{IEEE} International Conference on Information and Automation, {ICIA} 2016, Ningbo, China, August 1-3, 2016}, pages = {1126--1131}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICInfA.2016.7831988}, doi = {10.1109/ICINFA.2016.7831988}, timestamp = {Mon, 09 Aug 2021 14:54:01 +0200}, biburl = {https://dblp.org/rec/conf/icinfa/SuLW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XieLW16, author = {Xurong Xie and Xunying Liu and Lan Wang}, editor = {Nelson Morgan}, title = {Deep Neural Network Based Acoustic-to-Articulatory Inversion Using Phone Sequence Information}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {1497--1501}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-659}, doi = {10.21437/INTERSPEECH.2016-659}, timestamp = {Mon, 26 Jun 2023 16:43:56 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XieLW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LanchantinGKLQW16, author = {Pierre Lanchantin and Mark J. F. Gales and Penny Karanasou and Xunying Liu and Yanman Qian and Linlin Wang and Philip C. Woodland and Chao Zhang}, editor = {Nelson Morgan}, title = {Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems}, booktitle = {Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016}, pages = {3057--3061}, publisher = {{ISCA}}, year = {2016}, url = {https://doi.org/10.21437/Interspeech.2016-462}, doi = {10.21437/INTERSPEECH.2016-462}, timestamp = {Thu, 18 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/LanchantinGKLQW16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/SuLW15, author = {Rongfeng Su and Xunying Liu and Lan Wang}, title = {Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition}, journal = {{IEEE} {ACM} Trans. Audio Speech Lang. Process.}, volume = {23}, number = {1}, pages = {102--114}, year = {2015}, url = {https://doi.org/10.1109/TASLP.2014.2372901}, doi = {10.1109/TASLP.2014.2372901}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/taslp/SuLW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/ChenLGW15, author = {Xie Chen and Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Investigation of back-off based interpolation between recurrent neural network and n-gram language models}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {181--186}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404792}, doi = {10.1109/ASRU.2015.7404792}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/ChenLGW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/WoodlandLQZGKLW15, author = {Philip C. Woodland and Xunying Liu and Yanmin Qian and Chao Zhang and Mark J. F. Gales and Penny Karanasou and Pierre Lanchantin and Linlin Wang}, title = {Cambridge university transcription systems for the multi-genre broadcast challenge}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {639--646}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404856}, doi = {10.1109/ASRU.2015.7404856}, timestamp = {Tue, 23 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/WoodlandLQZGKLW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/LanchantinGKLQW15, author = {Pierre Lanchantin and Mark J. F. Gales and Penny Karanasou and Xunying Liu and Yanmin Qian and Linlin Wang and Philip C. Woodland and Chao Zhang}, title = {The development of the cambridge university alignment systems for the multi-genre broadcast challenge}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {647--653}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404857}, doi = {10.1109/ASRU.2015.7404857}, timestamp = {Tue, 23 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/LanchantinGKLQW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/KaranasouGLLQWW15, author = {Penny Karanasou and Mark J. F. Gales and Pierre Lanchantin and Xunying Liu and Yanmin Qian and Linlin Wang and Philip C. Woodland and Chao Zhang}, title = {Speaker diarisation and longitudinal linking in multi-genre broadcast data}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {660--666}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404859}, doi = {10.1109/ASRU.2015.7404859}, timestamp = {Tue, 23 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/KaranasouGLLQWW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/BellGHKLLMRSWW15, author = {Peter Bell and Mark J. F. Gales and Thomas Hain and Jonathan Kilgour and Pierre Lanchantin and Xunying Liu and Andrew McParland and Steve Renals and Oscar Saz and Mirjam Wester and Philip C. Woodland}, title = {The {MGB} challenge: Evaluating multi-genre broadcast media recognition}, booktitle = {2015 {IEEE} Workshop on Automatic Speech Recognition and Understanding, {ASRU} 2015, Scottsdale, AZ, USA, December 13-17, 2015}, pages = {687--693}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ASRU.2015.7404863}, doi = {10.1109/ASRU.2015.7404863}, timestamp = {Fri, 09 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/asru/BellGHKLLMRSWW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenLGW15, author = {Xie Chen and Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Improving the training and evaluation efficiency of recurrent neural network language models}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5401--5405}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7179003}, doi = {10.1109/ICASSP.2015.7179003}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenLGW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuCGW15, author = {Xunying Liu and Xie Chen and Mark J. F. Gales and Philip C. Woodland}, title = {Paraphrastic recurrent neural network language models}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5406--5410}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7179004}, doi = {10.1109/ICASSP.2015.7179004}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiuCGW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/ChenLGW15a, author = {Xie Chen and Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Recurrent neural network language model training with noise contrastive estimation for speech recognition}, booktitle = {2015 {IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2015, South Brisbane, Queensland, Australia, April 19-24, 2015}, pages = {5411--5415}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICASSP.2015.7179005}, doi = {10.1109/ICASSP.2015.7179005}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/ChenLGW15a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icinfa/WangXSWL15, author = {Wei Wang and Wenying Xu and Xiang Sui and Lan Wang and Xunying Liu}, title = {Investigations of low resource multi-accent mandarin speech recognition}, booktitle = {{IEEE} International Conference on Information and Automation, {ICIA} 2015, Lijiang, China, August 8-10, 2015}, pages = {62--66}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICInfA.2015.7279259}, doi = {10.1109/ICINFA.2015.7279259}, timestamp = {Mon, 09 Aug 2021 14:54:01 +0200}, biburl = {https://dblp.org/rec/conf/icinfa/WangXSWL15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XieLWS15, author = {Xurong Xie and Xunying Liu and Lan Wang and Rongfeng Su}, title = {Generalized variable parameter HMMs based acoustic-to-articulatory inversion}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {279--283}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-117}, doi = {10.21437/INTERSPEECH.2015-117}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XieLWS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/SuXLW15, author = {Rongfeng Su and Xurong Xie and Xunying Liu and Lan Wang}, title = {Efficient use of {DNN} bottleneck features in generalized variable parameter HMMs for noise robust speech recognition}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {2474--2478}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-534}, doi = {10.21437/INTERSPEECH.2015-534}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/SuXLW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuFWZGW15, author = {Xunying Liu and Federico Flego and Linlin Wang and Chao Zhang and Mark J. F. Gales and Philip C. Woodland}, title = {The Cambridge University 2014 {BOLT} conversational telephone Mandarin Chinese {LVCSR} system for speech translation}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {3145--3149}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-633}, doi = {10.21437/INTERSPEECH.2015-633}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuFWZGW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChenTLLWGW15, author = {Xie Chen and T. Tan and Xunying Liu and Pierre Lanchantin and M. Wan and Mark J. F. Gales and Philip C. Woodland}, title = {Recurrent neural network language model adaptation for multi-genre broadcast speech recognition}, booktitle = {{INTERSPEECH} 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015}, pages = {3511--3515}, publisher = {{ISCA}}, year = {2015}, url = {https://doi.org/10.21437/Interspeech.2015-696}, doi = {10.21437/INTERSPEECH.2015-696}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChenTLLWGW15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/csl/LiuGW14, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Paraphrastic language models}, journal = {Comput. Speech Lang.}, volume = {28}, number = {6}, pages = {1298--1316}, year = {2014}, url = {https://doi.org/10.1016/j.csl.2014.04.004}, doi = {10.1016/J.CSL.2014.04.004}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/csl/LiuGW14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuGW14, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Paraphrastic neural network language models}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {4903--4907}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6854534}, doi = {10.1109/ICASSP.2014.6854534}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuGW14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuWCGW14, author = {Xunying Liu and Yongqiang Wang and Xie Chen and Mark J. F. Gales and Philip C. Woodland}, title = {Efficient lattice rescoring using recurrent neural network language models}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {4908--4912}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6854535}, doi = {10.1109/ICASSP.2014.6854535}, timestamp = {Tue, 24 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icassp/LiuWCGW14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChenWLGW14, author = {Xie Chen and Yongqiang Wang and Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {641--645}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-163}, doi = {10.21437/INTERSPEECH.2014-163}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChenWLGW14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/XieSLW14, author = {Xurong Xie and Rongfeng Su and Xunying Liu and Lan Wang}, editor = {Haizhou Li and Helen M. Meng and Bin Ma and Engsiong Chng and Lei Xie}, title = {Deep neural network bottleneck features for generalized variable parameter HMMs}, booktitle = {{INTERSPEECH} 2014, 15th Annual Conference of the International Speech Communication Association, Singapore, September 14-18, 2014}, pages = {2739--2743}, publisher = {{ISCA}}, year = {2014}, url = {https://doi.org/10.21437/Interspeech.2014-158}, doi = {10.21437/INTERSPEECH.2014-158}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/XieSLW14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/csl/LiuGW13, author = {Xunying Liu and Mark John Francis Gales and Philip C. Woodland}, title = {Use of contexts in language model interpolation and adaptation}, journal = {Comput. Speech Lang.}, volume = {27}, number = {1}, pages = {301--321}, year = {2013}, url = {https://doi.org/10.1016/j.csl.2012.06.004}, doi = {10.1016/J.CSL.2012.06.004}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/csl/LiuGW13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/csl/LiuGW13a, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Language model cross adaptation for {LVCSR} system combination}, journal = {Comput. Speech Lang.}, volume = {27}, number = {4}, pages = {928--942}, year = {2013}, url = {https://doi.org/10.1016/j.csl.2012.07.010}, doi = {10.1016/J.CSL.2012.07.010}, timestamp = {Thu, 20 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/csl/LiuGW13a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/SuLW13, author = {Rongfeng Su and Xunying Liu and Lan Wang}, title = {Automatic model complexity control for generalized variable parameter HMMs}, booktitle = {2013 {IEEE} Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, December 8-12, 2013}, pages = {150--155}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ASRU.2013.6707721}, doi = {10.1109/ASRU.2013.6707721}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/asru/SuLW13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuGW13, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Paraphrastic language models and combination with neural network language models}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2013, Vancouver, BC, Canada, May 26-31, 2013}, pages = {8421--8425}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICASSP.2013.6639308}, doi = {10.1109/ICASSP.2013.6639308}, timestamp = {Fri, 03 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuGW13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/Lanchantin13, author = {Pierre Lanchantin and Peter Bell and Mark J. F. Gales and Thomas Hain and Xunying Liu and Yanhua Long and Jennifer Quinnell and Steve Renals and Oscar Saz and Matthew Stephen Seigel and Pawel Swietojanski and Philip C. Woodland}, editor = {Guillaume Gravier and Fr{\'{e}}d{\'{e}}ric B{\'{e}}chet}, title = {Automatic Transcription of Multi-genre Media Archives}, booktitle = {Proceedings of the First Workshop on Speech, Language and Audio in Multimedia, Marseille, France, August 22-23, 2013}, series = {{CEUR} Workshop Proceedings}, volume = {1012}, pages = {26--31}, publisher = {CEUR-WS.org}, year = {2013}, url = {https://ceur-ws.org/Vol-1012/papers/paper-05.pdf}, timestamp = {Fri, 10 Mar 2023 16:22:16 +0100}, biburl = {https://dblp.org/rec/conf/interspeech/Lanchantin13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LongGLLSW13, author = {Yanhua Long and Mark J. F. Gales and Pierre Lanchantin and Xunying Liu and Matthew Stephen Seigel and Philip C. Woodland}, 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 = {Improving lightly supervised training for broadcast transcription}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {2187--2191}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-516}, doi = {10.21437/INTERSPEECH.2013-516}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LongGLLSW13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiLW13, author = {Yang Li and Xunying Liu and Lan Wang}, 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 = {Feature space generalized variable parameter HMMs for noise robust recognition}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {2968--2972}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-271}, doi = {10.21437/INTERSPEECH.2013-271}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiLW13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuGW13, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, 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 = {Cross-domain paraphrasing for improving language modelling using out-of-domain data}, booktitle = {{INTERSPEECH} 2013, 14th Annual Conference of the International Speech Communication Association, Lyon, France, August 25-29, 2013}, pages = {3424--3428}, publisher = {{ISCA}}, year = {2013}, url = {https://doi.org/10.21437/Interspeech.2013-750}, doi = {10.21437/INTERSPEECH.2013-750}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuGW13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuGW12, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Paraphrastic Language Models}, booktitle = {{INTERSPEECH} 2012, 13th Annual Conference of the International Speech Communication Association, Portland, Oregon, USA, September 9-13, 2012}, pages = {1656--1659}, publisher = {{ISCA}}, year = {2012}, url = {https://doi.org/10.21437/Interspeech.2012-454}, doi = {10.21437/INTERSPEECH.2012-454}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuGW12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iscslp/LiLW12, author = {Yang Li and Xunying Liu and Lan Wang}, title = {Structured modeling based on generalized variable parameter HMMs and speaker adaptation}, booktitle = {8th International Symposium on Chinese Spoken Language Processing, {ISCSLP} 2012, Kowloon Tong, China, December 5-8, 2012}, pages = {136--140}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ISCSLP.2012.6423526}, doi = {10.1109/ISCSLP.2012.6423526}, timestamp = {Wed, 16 Oct 2019 14:14:48 +0200}, biburl = {https://dblp.org/rec/conf/iscslp/LiLW12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/slt/BellGLLLRSW12, author = {Peter Bell and Mark J. F. Gales and Pierre Lanchantin and Xunying Liu and Yanhua Long and Steve Renals and Pawel Swietojanski and Philip C. Woodland}, title = {Transcription of multi-genre media archives using out-of-domain data}, booktitle = {2012 {IEEE} Spoken Language Technology Workshop (SLT), Miami, FL, USA, December 2-5, 2012}, pages = {324--329}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/SLT.2012.6424244}, doi = {10.1109/SLT.2012.6424244}, timestamp = {Fri, 03 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/slt/BellGLLLRSW12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/chinaf/ChengLW11, author = {Ning Cheng and Xunying Liu and Lan Wang}, title = {A flexible framework for {HMM} based noise robust speech recognition using generalized parametric space polynomial regression}, journal = {Sci. China Inf. Sci.}, volume = {54}, number = {12}, pages = {2481--2491}, year = {2011}, url = {https://doi.org/10.1007/s11432-011-4490-6}, doi = {10.1007/S11432-011-4490-6}, timestamp = {Thu, 15 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/chinaf/ChengLW11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuGHW11, author = {Xunying Liu and Mark John Francis Gales and Jim L. Hieronymus and Philip C. Woodland}, title = {Investigation of acoustic units for {LVCSR} systems}, 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 = {4872--4875}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ICASSP.2011.5947447}, doi = {10.1109/ICASSP.2011.5947447}, timestamp = {Fri, 19 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuGHW11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ChengLW11, author = {Ning Cheng and Xunying Liu and Lan Wang}, title = {Generalized Variable Parameter HMMs for Noise Robust Speech Recognition}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {481--484}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-201}, doi = {10.21437/INTERSPEECH.2011-201}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ChengLW11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/DiehlGLTW11, author = {Frank Diehl and Mark John Francis Gales and Xunying Liu and Marcus Tomalin and Philip C. Woodland}, title = {Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {777--780}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-176}, doi = {10.21437/INTERSPEECH.2011-176}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/DiehlGLTW11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuGW11, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Improving {LVCSR} System Combination Using Neural Network Language Model Cross Adaptation}, booktitle = {{INTERSPEECH} 2011, 12th Annual Conference of the International Speech Communication Association, Florence, Italy, August 27-31, 2011}, pages = {2857--2860}, publisher = {{ISCA}}, year = {2011}, url = {https://doi.org/10.21437/Interspeech.2011-715}, doi = {10.21437/INTERSPEECH.2011-715}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuGW11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuGHW10, author = {Xunying Liu and Mark J. F. Gales and Jim L. Hieronymus and Philip C. Woodland}, title = {Language model combination and adaptation usingweighted finite state transducers}, 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 = {5390--5393}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ICASSP.2010.5494941}, doi = {10.1109/ICASSP.2010.5494941}, timestamp = {Fri, 19 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuGHW10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuGW10, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Language model cross adaptation for {LVCSR} system combination}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {342--345}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-126}, doi = {10.21437/INTERSPEECH.2010-126}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuGW10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/ParkLGW10, author = {Junho Park and Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, editor = {Takao Kobayashi and Keikichi Hirose and Satoshi Nakamura}, title = {Improved neural network based language modelling and adaptation}, booktitle = {{INTERSPEECH} 2010, 11th Annual Conference of the International Speech Communication Association, Makuhari, Chiba, Japan, September 26-30, 2010}, pages = {1041--1044}, publisher = {{ISCA}}, year = {2010}, url = {https://doi.org/10.21437/Interspeech.2010-342}, doi = {10.21437/INTERSPEECH.2010-342}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/ParkLGW10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuGW09, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Use of contexts in language model interpolation and adaptation}, booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009}, pages = {360--363}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-115}, doi = {10.21437/INTERSPEECH.2009-115}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuGW09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/HieronymusLGW09, author = {Jim L. Hieronymus and Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Exploiting Chinese character models to improve speech recognition performance}, booktitle = {{INTERSPEECH} 2009, 10th Annual Conference of the International Speech Communication Association, Brighton, United Kingdom, September 6-10, 2009}, pages = {364--367}, publisher = {{ISCA}}, year = {2009}, url = {https://doi.org/10.21437/Interspeech.2009-116}, doi = {10.21437/INTERSPEECH.2009-116}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/HieronymusLGW09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/interspeech/LiuGW08, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Context dependent language model adaptation}, booktitle = {{INTERSPEECH} 2008, 9th Annual Conference of the International Speech Communication Association, Brisbane, Australia, September 22-26, 2008}, pages = {837--840}, publisher = {{ISCA}}, year = {2008}, url = {https://doi.org/10.21437/Interspeech.2008-254}, doi = {10.21437/INTERSPEECH.2008-254}, timestamp = {Fri, 23 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/interspeech/LiuGW08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/LiuG07, author = {Xunying Liu and Mark J. F. Gales}, title = {Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {15}, number = {4}, pages = {1414--1424}, year = {2007}, url = {https://doi.org/10.1109/TASL.2006.889804}, doi = {10.1109/TASL.2006.889804}, timestamp = {Sun, 17 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/LiuG07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/asru/LiuBGGTWY07, author = {Xunying Liu and William J. Byrne and Mark J. F. Gales and Adri{\`{a}} de Gispert and Marcus Tomalin and Philip C. Woodland and Kai Yu}, editor = {Sadaoki Furui and Tatsuya Kawahara}, title = {Discriminative language model adaptation for Mandarin broadcast speech transcription and translation}, booktitle = {{IEEE} Workshop on Automatic Speech Recognition {\&} Understanding, {ASRU} 2007, Kyoto, Japan, December 9-13, 2007}, pages = {153--158}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ASRU.2007.4430101}, doi = {10.1109/ASRU.2007.4430101}, timestamp = {Thu, 10 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/asru/LiuBGGTWY07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/TomalinGLSSWWY07, author = {Marcus Tomalin and Mark J. F. Gales and X. Andrew Liu and Khe Chai Sim and Rohit Sinha and Lan Wang and Philip C. Woodland and Kai Yu}, title = {Improving Speech Transcription for Mandarin-English Translation}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April 15-20, 2007}, pages = {97--100}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ICASSP.2007.367172}, doi = {10.1109/ICASSP.2007.367172}, timestamp = {Tue, 08 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/TomalinGLSSWWY07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/GalesLSWYMNNNGLM07, author = {Mark J. F. Gales and Xunying Liu and Rohit Sinha and Philip C. Woodland and Kai Yu and Spyros Matsoukas and Tim Ng and Kham Nguyen and Long Nguyen and Jean{-}Luc Gauvain and Lori Lamel and Abdelkhalek Messaoudi}, title = {Speech Recognition System Combination for Machine Translation}, booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2007, Honolulu, Hawaii, USA, April 15-20, 2007}, pages = {1277--1280}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ICASSP.2007.367310}, doi = {10.1109/ICASSP.2007.367310}, timestamp = {Tue, 08 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/GalesLSWYMNNNGLM07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/HainWEGLMPW06, author = {Thomas Hain and Philip C. Woodland and Gunnar Evermann and Mark J. F. Gales and Xunying Liu and Gareth L. Moore and Daniel Povey and Lan Wang}, title = {Corrections to "Automatic Transcription of Conversational Telephone Speech"}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {14}, number = {2}, pages = {727--727}, year = {2006}, url = {https://doi.org/10.1109/TASL.2006.871051}, doi = {10.1109/TASL.2006.871051}, timestamp = {Fri, 03 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/HainWEGLMPW06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/SinhaGKLSW06, author = {Rohit Sinha and Mark J. F. Gales and Do Yeong Kim and X. Andrew Liu and Khe Chai Sim and Philip C. Woodland}, title = {The Cu-Htk Mandarin Broadcast News Transcription System}, booktitle = {2006 {IEEE} International Conference on Acoustics Speech and Signal Processing, {ICASSP} 2006, Toulouse, France, May 14-19, 2006}, pages = {1077--1080}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/ICASSP.2006.1660211}, doi = {10.1109/ICASSP.2006.1660211}, timestamp = {Tue, 08 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/SinhaGKLSW06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/taslp/HainWEGLMPW05, author = {Thomas Hain and Philip C. Woodland and Gunnar Evermann and Mark J. F. Gales and Xunying Liu and Gareth L. Moore and Daniel Povey and Lan Wang}, title = {Automatic transcription of conversational telephone speech}, journal = {{IEEE} Trans. Speech Audio Process.}, volume = {13}, number = {6}, pages = {1173--1185}, year = {2005}, url = {https://doi.org/10.1109/TSA.2005.852999}, doi = {10.1109/TSA.2005.852999}, timestamp = {Fri, 09 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/taslp/HainWEGLMPW05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/GalesJLSWY05, author = {Mark J. F. Gales and Bin Jia and X. Andrew Liu and Khe Chai Sim and Philip C. Woodland and Kai Yu}, title = {Development of the {CUHTK} 2004 Mandarin Conversational Telephone Speech Transcription System}, booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23, 2005}, pages = {841--844}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/ICASSP.2005.1415245}, doi = {10.1109/ICASSP.2005.1415245}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/GalesJLSWY05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuGSY05, author = {Xunying Liu and Mark J. F. Gales and Khe Chai Sim and Kai Yu}, title = {Investigation of Acoustic Modeling Techniques for {LVCSR} Systems}, booktitle = {2005 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '05, Philadelphia, Pennsylvania, USA, March 18-23, 2005}, pages = {849--852}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/ICASSP.2005.1415247}, doi = {10.1109/ICASSP.2005.1415247}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuGSY05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/EvermannCGHLMWW04, author = {Gunnar Evermann and Ho Yin Chan and Mark J. F. Gales and Thomas Hain and Xunying Liu and David Mrva and Lan Wang and Philip C. Woodland}, title = {Development of the 2003 {CU-HTK} conversational telephone speech transcription system}, booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004}, pages = {249--252}, publisher = {{IEEE}}, year = {2004}, url = {https://doi.org/10.1109/ICASSP.2004.1325969}, doi = {10.1109/ICASSP.2004.1325969}, timestamp = {Fri, 09 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/EvermannCGHLMWW04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuG04, author = {Xunying Liu and Mark J. F. Gales}, title = {Model complexity control and compression using discriminative growth functions}, booktitle = {2004 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} 2004, Montreal, Quebec, Canada, May 17-21, 2004}, pages = {797--800}, publisher = {{IEEE}}, year = {2004}, url = {https://doi.org/10.1109/ICASSP.2004.1326106}, doi = {10.1109/ICASSP.2004.1326106}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuG04.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/LiuGW03, author = {Xunying Liu and Mark J. F. Gales and Philip C. Woodland}, title = {Automatic complexity control for {HLDA} systems}, booktitle = {2003 {IEEE} International Conference on Acoustics, Speech, and Signal Processing, {ICASSP} '03, Hong Kong, April 6-10, 2003}, pages = {132--135}, publisher = {{IEEE}}, year = {2003}, url = {https://doi.org/10.1109/ICASSP.2003.1198734}, doi = {10.1109/ICASSP.2003.1198734}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icassp/LiuGW03.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.