Prof. LIU, Xunying
劉 循 英 教授
Associate Professor
BSc (Shanghai Jiao Tong University)
MPhil (University of Cambridge)
PhD (University of Cambridge)
Research Interests :
* Machine learning
* Large vocabulary continuous speech recognition
* Language modelling
* Speech synthesis
* Speech and language processing
* Assitive technologies
* Big data analytics
Office: Room 708, William M.W. Mong Engineering Building
Tel: (852) 3943-8318
Email: xyliu@se.cuhk.edu.hk
Biography
Xunying Liu received his PhD degree in speech recognition and MPhil degree in computer speech and language processing both from University of Cambridge, after his undergraduate study at Shanghai Jiao Tong University. He was a Senior Research Associate at the Machine Intelligence Laboratory of the Cambridge University Engineering Department, prior to joining the Department of Systems Engineering and Engineering Management, Chinese University of Hong Kong, as an Associate Professor in 2016. Dr. Xunying has published more than 130 referred journal and conference articles in top venues of speech technology and artificial intelligence including IEEE/ACM Transactions on Audio, Speech and Language Processing, Computer Speech and Language, Journal of the Acoustical Society of America, IEEE ICASSP, ISCA Interspeech, IEEE ASRU and IEEE CVPR. He and his students were the recipients of a number of best paper awards and nominations, including a Best Paper Award at ISCA Interspeech2010 for the paper titled “Language model cross adaptation for LVCSR system combination”, and a Best Student Paper Award at IEEE ICASSP2019 for the paper titled “BLHUC: Bayesian learning of hidden unit contributions for deep neural network adaptation”. He is a co-author of the widely used HTK speech recognition toolkit. His research outputs led to several large scale speech recognition systems that were top ranked in international research evaluations supported by DARPA and EPSRC UK. These include the Cambridge Mandarin broadcast and conversational telephone speech recognition systems from 2006 to 2014, and the Cambridge 2015 multi-genre BBC broadcast speech transcription system. His recent research has been supported by Hong Kong Research Grants Council General Research Fund and Theme-based Research Scheme, Hong Kong Innovation and Technology Commission, Shun Hing Institute of Advanced Engineering and Microsoft Research Asia. He is a regular reviewer for top speech technology journals including IEEE/ACM Transactions on Audio, Speech and Language Processing, Computer Speech and Language and Speech Communication. He has served as a member of the scientific or organization committees for conferences including recently ISCA Interspeech2020 and IEEE SLT2021. Dr. Xunying Liu is a member of IEEE and ISCA.
Best Papers
Xurong Xie, Xunying Liu, Tan Lee, Shoukang Hu, Lan Wang. BLHUC: BAYESIAN LEARNING OF HIDDEN UNIT CONTRIBUTIONS FOR DEEP NEURAL NETWORK SPEAKER ADAPTATION, Best Student Paper Award, IEEE ICASSP2019, Brighton, UK.
Shansong Liu, Shoukang Hu, Yi Wang, Jianwei Yu, Rongfeng Su, Xunying Liu, Helen Meng. Exploiting Visual Features using Bayesian Gated Neural Networks for Disordered Speech Recognition, ISCA Student Paper Award Nomination, ISCA Interspeech2019, Graz, Austria.
Xunying Liu, Yongqian Wang, Xie Chen, Mark J. F. Gales, Philip C. Woodland. Efficient Lattice Rescoring Using Recurrent Neural Network Language Models, Paper Award Nomination, IEEE ICASSP2014, Florence, Italy.
Xunying Liu, Mark J. F. Gales, Philip C. Woodland. Language Model Cross Adaptation For LVCSR System Combination, Best Paper Award, ISCA Interspeech2010, Makuhari, Japan.
Selected Publications
Shoukang Hu, Xurong Xie, Shansong Liu, Jianwei Yu, Zi Ye, Mengzhe Geng, Xunying Liu and Helen Meng. Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 29, 1514-1529, 2021. DOI: 10.1109/TASLP.2021.3069080
Jianwei Yu, Shi-Xiong Zhang, Bo, Wu, Shansong Liu, Shoukang Hu, Mengzhe Geng, Xunying Liu, Helen Meng, Dong Yu. Audio-visual Multi-Channel Integration and Recognition of Overlapped Speech, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 29, Pages 2067-2082, 2021.
DOI: 10.1109/TASLP.2021.3078883
Xurong Xie, Xunying Liu, Tan Lee, Lang Wang. Bayesian Learning for Deep Neural Network Adaptation, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 29, Pages 2096-2110, 2021. DOI: 10.1109/TASLP.2021.3084072
Shansong Liu, Mengzhe Geng, Shoukang Hu, Xurong Xie, Mingyu Cui, Jianwei Yu, Xunying Liu, Helen Meng. Recent Progress in the CUHK Dysarthric Speech Recognition System, forthcoming in IEEE/ACM Transactions on Audio, Speech and Language Processing, 2021. DOI: 10.1109/TASLP.2021.3091805
Xixin Wu, Yuewen Cao, Hui Lu, Songxiang Liu, Shiyin Kang, Zhiyong Wu, Xunying Liu and Helen Meng. Exemplar-based Emotive Speech Synthesis, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 29, 874-886, 2021.
DOI: 10.1109/TASLP.2021.3052688
Songxiang Liu, Yuewen Cao, Disong Wang, Xixin Wu, Xunying Liu and Helen Meng. Any-to- Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 29, 1717-1728, 2021. DOI: 10.1109/TASLP.2021.3076867
Rongfeng Su, Xunying Liu, Lan Wang and Jingzhou Yang. Cross-Domain Deep Visual Feature Generation for Mandarin Audio-Visual Speech Recognition, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 28, Issue 1, December 2020, Pages 185-197. DOI: 10.1109/TASLP.2019.2950602
Xie Chen, Xunying Liu, Yu Wang, Anton Ragni, Jeremy Wong and Mark. J. F. Gales. Exploiting Future Word Contexts in Neural Network Language Models for Speech Recognition, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 27, Issue 9, September 2019, Pages 1444-1454. DOI: 10.1109/TASLP.2019.2922048
Cai Wingfiled, Li Su, Xunying Liu, Chao Zhang, Philip C. Woodland, Andrew Thwaites, Elisabeth Fonteneau and William D. Marslen-Wilson. Relating Dynamic Brain States to Dynamic Machine States: Human and Machine Solutions to the Speech Recognition Problem, September 2017, PLoS Computational Biology 13(9):e1005617. https://doi.org/10.1371/journal.pcbi.1005617
Xie Chen, Xunying Liu, Yongqiang Wang, Mark J. F. Gales and Philip C. Woodland. Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 24, Issue 11, November 2016, Pages 2146-2157. DOI: 10.1109/TASLP.2016.2598304
Xunying Liu, Xie Chen, Yongqiang Wang, Mark J. F. Gales and Philip C. Woodland. Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models, IEEE/ACM Transactions on Audio, Speech and Language Processing, Volume 24, Issue 8, August 2016, Pages 1438-1449. DOI: 10.1109/TASLP.2016.2558826
Shoukang Hu, Xurong Xie, Shansong Liu, Mingyu Cui, Mengzhe Geng, Xunying Liu, Helen Meng. Neural Architecture Search for LF-MMI Trained Time Delay Neural Networks, IEEE ICASSP2021, Toronto, Canada.
Zi Ye, Shoukang Hu, Jinchao Li, Xurong Xie, Mengzhe Geng, Jianwei Yu, Junhao Xu, Boyang Xue, Shansong Liu, Xunying Liu, Helen Meng. DEVELOPMENT OF THE CUHK ELDERLY SPEECH RECOGNITION SYSTEM FOR NEUROCOGNITIVE DISORDER DETECTION USING THE DEMENTIABANK CORPUS, IEEE ICASSP2021, Toronto, Canada.
Junhao Xu, Jianwei Yu, Shoukang Hu, Xunying Liu, Helen Meng. MIXED PRECISION QUANTIZATION OF TRANSFORMER LANGUAGE MODELS FOR SPEECH RECOGNITION, IEEE ICASSP2021, Toronto, Canada.
Boyang Xue, Jianwei Yu, Junhao Xu, Shansong Liu, Shoukang Hu, Zi Ye, Mengzhe Geng, Xunying Liu, Helen Meng. BAYESIAN TRANSFORMER LANGUAGE MODELS FOR SPEECH RECOGNITION, IEEE ICASSP2021, Toronto, Canada.
Jianwei Yu, Bo Wu, Rongzhi Gu, Shixiong Zhang, Lianwu Chen, Yong Xu, Meng Yu, Dan Su, Dong Yu, Xunying Liu, Helen Meng. Audio-visual Multi-channel Recognition of Overlapped Speech, ISCA Interspeech2020, Shanghai, China.
Mengzhe Geng, Xurong Xie, Shansong Liu, Jianwei Yu, Shoukang Hu, Xunying Liu, Helen Meng. Investigation of Data Augmentation Techniques for Disordered Speech Recognition, ISCA Interspeech2020, Shanghai, China.
Shansong Liu, Xurong Xie, Jianwei Yu, Shoukang Hu, Mengzhe Geng, Rongfeng Su, Shixiong Zhang, Xunying Liu, Helen Meng. Exploiting Cross Domain Visual Feature Generation for Disordered Speech Recognition, ISCA Interspeech2020, Shanghai, China.
Shoukang Hu, Sirui Xie, Hehui Zheng, Chunxiao Liu, Jianping Shi, Xunying Liu, Dahua Lin. DSNAS: Direct Neural Architecture Search without Parameter Retraining, IEEE/CVF CVPR2020, Seattle WA, USA.
Xurong Xie, Xunying Liu, Tan Lee, Shoukang Hu, Lan Wang. BLHUC: BAYESIAN LEARNING OF HIDDEN UNIT CONTRIBUTIONS FOR DEEP NEURAL NETWORK SPEAKER ADAPTATION, Best Student Paper Award, IEEE ICASSP2019, Brighton, UK.
Shansong Liu, Shoukang Hu, Yi Wang, Jianwei Yu, Rongfeng Su, Xunying Liu and Helen Meng. Exploiting Visual Features using Bayesian Gated Neural Networks for Disordered Speech Recognition, ISCA Student Paper Award Nomination, ISCA Interspeech2019, Graz, Austria.
Jianwei Yu, Xurong Xie, Shoukang Hu, Shansong Liu, Max W. Y. Lam, Xixin Wu, Ka Ho Wong, Xunying Liu and Helen Meng Development of the CUHK Dysarthric Speech Recognition System for the UA Speech Corpus, ISCA Interspeech2018, Hyderabad, India.