Selected Publications

X. Liu (2005). Discriminative Complexity Control and Linear Projections for Large Vocabulary Speech Recognition, PhD thesis, Cambridge University.

S. J. Young, G. Evermann, M. J. F. Gales, T. Hain, D. Kershaw, X. Liu, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev and P. C. Woodland. The HTK Book Version 3.4.1, 2009.

M. Tomalin, W. Byrne, A. de Gispert, M. Gales, X. Liu, P. Woodland et al. ``Improving Speech Transcription for Machine Translation'', in J. Olive, C. Christianson, and J. McCary, editors, Handbook of natural language processing and machine translation. DARPA Global Autonomous Language Exploitation. Springer, ISBN 978-1-4419-7712-0, 2011.
S. Matsoukas, T. Ng , L. Nguyen , F. Diehl, M. J. F. Gales, X. Liu, P. C. Woodland, J-L Gauvain, L. Lamel, A. Messaoudi et al. ``Optimizing Speech-To-Text System Combination for Machine Translation'', in J. Olive, C. Christianson, and J. McCary, editors, Handbook of natural language processing and machine translation. DARPA Global Autonomous Language Exploitation. Springer, ISBN 978-1-4419-7712-0, 2011.

T. Hain, P. C. Woodland, G. Evermann, M. J. F. Gales, X. Liu, G.L. Moore, D. Povey and L. Wang. Automatic Transcription of Conversational Telephone Speech, IEEE Transactions on Speech and Audio Processing, Vol. 13, Nov. 2005.
X. Liu and M. J. F. Gales. Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions. IEEE Transactions on Speech and Audio Processing, Vol. 4, May 2007.
X. Liu, M. J. F. Gales and P. C. Woodland. Use of Contexts in Language Model Interpolation and Adaptation. Computer Speech and Language, Volume 27, Issue 1, January 2013. [pdf|web]
X. Liu, M. J. F. Gales and P. C. Woodland. Language Model Cross Adaptation For LVCSR System Combination. Computer Speech and Language, Volume 27, Issue 4, June 2013. [ pdf|web]
N. Cheng, X. Liu and L. Wang. A Flexible Framework for HMM Based Noise Robust Speech Recognition Using Generalized Parametric Space Polynomial Regression, SCIENCE CHINA Information Sciences, Volume 54, Number 12, 2481-2491, 2011.
X. Liu, J. L. Hieronymus, M. J. F. Gales and P. C. Woodland. Syllable Language Models for Mandarin Speech Recognition: Exploiting Character Sequence Models, Journal of the Acoustical Society of America, Volume 133, Issue 1, 519-528, January 2013. [ pdf|web]

X. Liu, M. J .F. Gales and P. C. Woodland. Automatic Complexity Control for HLDA Systems. IEEE ICASSP2003, Hong Kong.
X. Liu and M. J. F. Gales. A utomatic Model Complexity Control Using Marginalized Discriminative Growth Functions. IEEE ASRU 2003, St. Thomas, U.S. Virgine Islands.
X. Liu and M. J .F. Gales. Model Complexity Control and Compression Using Discriminative Growth Functions. IEEE ICASSP2004, Montreal.
G. Evermann, H. Y. Chan, M. J. F. Gales, T. Hain, X. Liu, D. Mrva, L. Wang and P. C. Woodland. Development of the 2003 CU-HTK Conversational Telephone Speech Transcription System. IEEE ICASSP2004, Montreal.
X. Liu, M. J. F. Gales, K. C. Sim and K. Yu. Investigation of Acoustic Modeling Techniques for LVCSR Systems. IEEE ICASSP2005, Philadelphia.
M. J. F. Gales, B. Jia, X. Liu, K. C. Sim, P. C. Woodland and K. Yu. Development of the CUHTK 2004 Mandarin Conversational Telephone Speech Transcription System. IEEE ICASSP2005, Philadelphia.
R. Sinha, M. J. F. Gales, D. Y. Kim, X. Liu, K. C. Kim and P. C. Woodland. The CU-HTK Mandarin Broadcast News Transcription System. IEEE ICASSP2006, Toulouse.
M.J.F. Gales , X. Liu , R. Sinha , P.C. Woodland , K. Yu , S. Matsoukas , T. Ng , K. Nguyen , L. Nguyen , J-L Gauvain , L. Lamel and A. Messaoudi. Speech Recognition System Combination For Machine Translation. IEEE ICASSP2007, Hawaii.
M. Tomalin, M.J.F. Gales, X. A. Liu, K.C. Sim, R. Sinha, L. Wang, P.C. Woodland and K. Yu. Improving Speech Transcription for Mandarin-English Translation. IEEE ICASSP2007, Hawaii.
X. Liu, W. J. Byrne, M. J. F. Gales, A. de Gispert, M. Tomalin, P. C. Woodland and K. Yu. Discriminative Language Model Adaptation for Mandarin Broadcast Speech Transcription and Translation, IEEE ASRU2007, Kyoto.
X. Liu, M. J. F. Gales and P. C. Woodland. Context Dependent Language Model Adaptation, ISCA InterSpeech2008, Brisbane.
X. Liu, M. J. F. Gales and P. C. Woodland. Use of Contexts in Language Model Interpolation and Adaptation, ISCA Interspeech2009, Brighton.
J. L. Hieronymus, X. Liu, M. J. F. Gales and P. C. Woodland. Exploiting Chinese Character Models to Improve Speech Recognition Performance, ISCA Interspeech2009, Brighton.
X. Liu, M. J. F. Gales, J. L. Hieronymus and P. C. Woodland. Language Model Combination and Adaptation Using Weighted Finite State Transducers, IEEE ICASSP2010, Dallas.
X. Liu, M. J. F. Gales and P. C. Woodland. Language Model Cross Adaptation For LVCSR System Combination, Best Paper Award , ISCA Interspeech2010, Makuhari, Japan.
J. Park, X. Liu, M. J. F. Gales and P. C. Woodland. Improved Neural Network Based Language Modelling and Adaptation, ISCA Interspeech2010, Makuhari, Japan.
X. Liu, M. J. F. Gales, J. L. Hieronymus and P. C. Woodland. Investigation of Acoustic Units for LVCSR Systems, IEEE ICASSP2011, Prague.
X. Liu, M. J. F. Gales and P. C. Woodland. Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation, ISCA Interspeech2011, Florence, Italy.
F. Diehl, M. J. F. Gales, X. Liu, M. Tomalin and P. C. Woodland. Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems, ISCA Interspeech2011, Florence, Italy.
N. Cheng, X. Liu and L. Wang Generalized Variable Parameter HMMs for Noise Robust Speech Recognition, ISCA Interspeech2011, Florence, Italy.
X. Liu, M. J. F. Gales and P. C. Woodland. Paraphrastic Language Models, ISCA Interspeech2012, Portland, Oregon.
P. Bell, M. Gales, P. Lanchantin, X. Liu, Y. Long, S. Renals, P. Swietojanski and P. Woodland. Transcription of Multi-genre Media Archives Using Out-of-domain Data, IEEE SLT2012, Miami, Florida.
Y. Li, X. Liu and L. Wang. Structured Modelling Based on Generalized Variable Parameter HMMs, ISCSLP2012, Hong Kong.
X. Liu, M. J. F. Gales and P. C. Woodland. Paraphrastic Language Models and Combination with Neural Network Language Models, to appear in IEEE ICASSP2013, Vancouver.
X. Liu, M. J. F. Gales and P. C. Woodland. Cross-domain Paraphrasing For Improving Language Modelling Using Out-of-domain Data, to appear in ISCA Interspeech2013, Lyon.
Y. Li, X. Liu and L. Wang Feature Space Generalized Variable Parameter HMMs for Noise Robust Recognition, to appear in ISCA Interspeech2013, Lyon.
Y. Long, M.J.F. Gales, P. Lanchantin, X. Liu, M.S. Seigel and P.C. Woodland Improving Lightly Supervised Training for Broadcast Transcription, to appear in ISCA Interspeech2013, Lyon.

T. Hain, P. C. Woodland, G. Evermann, X. Liu, G. L. Moore, D. Povey and L. Wang, Automatic Transcription of Conversational Telephone Speech. Development of the CU-HTK 2002 System. Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-465. December 2003.
X. Liu and M. J. F. Gales, Discriminative Training of Multiple Subspace Projections for Large Vocabulary Speech Recognition. Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-489. August 2004.
X. Liu and M. J. F. Gales, Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions. Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-490. August 2004.
X. Liu, W. J. Byrne, M. J. F. Gales and P. C. Woodland et al, Discriminative Language Model Adaptation for Mandarin Broadcast Speech Transcription and Translation. Cambridge University Engineering Department Technical Report,CUED/F-INFENG/TR-586. Sept. 2007.
X. Liu, M. J. F. Gales and P. C. Woodland, Use of Contexts in Language Model Interpolation and Adaptation. Cambridge University Engineering Department Technical Report, CUED/F-INFENG/TR-630. Februray 2009.

P. C. Woodland, G. Evermann, M. J. F. Gales, T. Hain, X. Liu, G. Moore, D. Povey and L. Wang (2002) CU-HTK APRIL 2002 SWITCHBOARD SYSTEM. Rich Transcription Workshop, 2002, Vienna, Virginia, U.S.
X. Liu, M. J. F. Gales and P. C. Woodland (2003) Automatic Complexity Control for HLDA Systems. Hong Kong, ICASSP 2003.
X. Liu and M. J. F. Gales (2003) Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions. DARPA EARS STT technical meeting, Martigny, Switzerland, September, 2003.
X. Liu and M. J. F. Gales (2004) Discriminative Model Complexity Control. Presentation to DARPA and GCHQ EARS Site Visit, August, 2004.
M. J. F. Gales, X. Liu, K. C. Sim and K. Yu (2004). Investigation of Acoustic Modeling Techniques for LVCSR Systems. DARPA EARS Rich Transcription Workshop 2004.
M. J. F. Gales, B. Jia, X. Liu, K. C. Sim, P. C. Woodland and K. Yu (2004). Development of the CUHTK 2004 Mandarin Conversational Telephone Speech Transcription System. DARPA EARS Rich Transcription Workshop 2004.
X. Liu, M. J. F. Gales and P. C. Woodland (2007). HTK Large Vocabulary Decoder and Discriminative Training Tools. Part of presentation on new features of HTK version 3.4, the HTK Meeting, Hawaii, 2007.
X. Liu, W. J. Byrne, M. J. F. Gales, P. C. Woodland (2007). Investigation of System Combination, Improved Minimum Bayes Risk Decoding, Discriminative Language Model Interpolation and Adaptation for Machine Translation. Part of joint AGILE team presentation to DARPA's GALE Site Visit, August, 2007.
A. de Gispert, X. Liu, W. J. Byrne, M. J. F. Gales and P. C. Woodland (2008) Broadcast Speech Transcription and Translation. Poster at Horizon Seminar: The Thinking Machine?, Emmanuel College, Cambridge, Mar 2008.
P. C. Woodland, X. Liu, M. J. F. Gales, K. Yu, T. Ng and L. Nguyen et al. (2008). Development of AGILE Chinese STT Systems. AGILE team presentation to DARPA's GALE Principal Invigilator Meeting, April, 2008.
X. Liu, M. J. F. Gales and P. C. Woodland (2008). Context Dependent Language Model Interpolation and Adaptation. Presentation at ISCA Interspeech2008; invited talk at the Chinese University of Hong Kong and Shenzhen Institute of Advanced technology, Chinese Academy of Sciences, September, 2008.
X. Liu, F. Diehl, M. Tomalin M. J. F. Gales and P. C. Woodland (2009). AGILE Speech to Text (STT), part of AGILE team presentation to DARPA's GALE Principal Invigilator Meeting, May, 2009.

[ Cambridge University|CUED | MIL ]