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, speech recognition
* language modelling, speech synthesis,
* speech and language processing
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. He was the recipient of best paper award at ISCA Interspeech2010 for his paper titled “Language Model Cross Adaptation For LVCSR System Combination”. He is a co-author of the widely used HTK toolkit and has continued to contribute to its current development in deep neural network based acoustic and language modelling. His research outputs led to several large scale speech recognition systems that were top ranked in a series of international research evaluations. These include the Cambridge Mandarin Chinese broadcast and conversational telephone speech recognition systems developed for the US government sponsored speech translation evaluations from 2006 to 2011, and the Cambridge 2015 multigenre broadcast speech transcription system. His current research interests include machine learning, large vocabulary continuous speech recognition, statistical language modelling, noise robust speech recognition, speech synthesis, speech and language processing. He is a regular reviewer for journals including IEEE/ACM Transactions on Audio, Speech and Language Processing, Computer Speech and Language, Speech Communication, the Journal of the Acoustical Society of America Express Letters, Language Resources and Evaluation, and Natural Language Engineering. He has served as a member of the scientific committee and session chair for conferences including IEEE ICASSP and ISCA Interspeech. Dr. Xunying Liu is a member of IEEE and ISCA.
Selected Publications
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.
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, to appear in IEEE/ACM Transactions on Audio, Speech and Language Processing.
Rongfeng Su, Xunying Liu, Lan Wang: Automatic Complexity Control of Generalized Variable Parameter HMMs for Noise Robust Speech Recognition. IEEE/ACM Trans. Audio, Speech & Language Processing 23(1): 102-114 (2015)
Xunying Liu, Mark J. F. Gales, Philip C. Woodland: Paraphrastic language models. Computer Speech & Language 28(6): 1298-1316 (2014)
Xunying Liu, Mark J. F. Gales, Philip C. Woodland: Use of contexts in language model interpolation and adaptation. Computer Speech & Language 27(1): 301-321 (2013)
Xunying Liu, Mark J. F. Gales, Philip C. Woodland: Language model cross adaptation for LVCSR system combination. Computer Speech & Language 27(4): 928-942 (2013)
Xunying Liu, James L. Hieronymus, Mark J. F. Gales and Philip C. Woodland: Syllable Language Models for Mandarin Speech Recognition: Exploiting Character Sequence Models, the Journal of the Acoustical Society of America, Volume 133, Issue 1, 519-528, January 2013.
Xie Chen, Xunying Liu, Yanmin Qian, Mark J. F. Gales, Philip C. Woodland: CUED-RNNLM An open-source toolkit for efficient training and evaluation of recurrent neural network language models, IEEE ICASSP 2016: 6000-6004
Linlin Wang, Chao Zhang, Philip C. Woodland, Mark J. F. Gales, Xunying Liu and Yanmin Qian: Improved DNN based segmentation for multi-genre broadcast audio, IEEE ICASSP 2016: 5700-5704
Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland: Investigation of back-off based interpolation between recurrent neural network and n-gram language models. IEEE ASRU 2015: 181-186
Philip C. Woodland, Xunying Liu, Yanmin Qian, Chao Zhang, Mark J. F. Gales, Penny Karanasou, Pierre Lanchantin, Linlin Wang: Cambridge university transcription systems for the multi-genre broadcast challenge. IEEE ASRU 2015: 639-646
Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang: The development of the cambridge university alignment systems for the multi-genre broadcast challenge. IEEE ASRU 2015: 647-653
Penny Karanasou, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang: Speaker diarisation and longitudinal linking in multi-genre broadcast data. IEEE ASRU 2015: 660-666
Peter Bell, Mark J. F. Gales, Thomas Hain, Jonathan Kilgour, Pierre Lanchantin, Xunying Liu, Andrew McParland, Steve Renals, Oscar Saz, Mirjam Wester, Philip C. Woodland: The MGB challenge: Evaluating multi-genre broadcast media recognition. IEEE ASRU 2015: 687-693
Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland: Improving the training and evaluation efficiency of recurrent neural network language models. IEEE ICASSP 2015: 5401-5405
Xunying Liu, Xie Chen, Mark J. F. Gales, Philip C. Woodland: Paraphrastic recurrent neural network language models. IEEE ICASSP 2015: 5406-5410
Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland: Recurrent neural network language model training with noise contrastive estimation for speech recognition. IEEE ICASSP 2015: 5411-5415
Xurong Xie, Xunying Liu, Lan Wang, Rongfeng Su: Generalized variable parameter HMMs based acoustic-to-articulatory inversion. ISCA INTERSPEECH 2015: 279-283
Rongfeng Su, Xurong Xie, Xunying Liu, Lan Wang: Efficient use of DNN bottleneck features in generalized variable parameter HMMs for noise robust speech recognition. ISCA INTERSPEECH 2015: 2474-2478
Xunying Liu, Federico Flego, Linlin Wang, Cao Zhang, Mark J. F. Gales, Philip C. Woodland: The cambridge university 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation. ISCA INTERSPEECH 2015: 3145-3149
Xie Chen, Tian Tan, Xunying Liu, Pierre Lanchantin, Moquan Wan, Mark J. F. Gales, Philip C. Woodland: Recurrent neural network language model adaptation for multigenre broadcast speech recognition. ISCA INTERSPEECH 2015: 3511-3515