Publications

A (possibly outdated) list of all my publications is available. If you want a postscript copy of any of these papers contact me by email mjfg@eng.cam.ac.uk. Some presentations are also available online.

[new] papers are available:

The Application of Hidden Markov Models in Speech Recognition. M.J.F. Gales and S.J. Young
Model-Based Approaches to Handling Uncertainty. M.J.F. Gales
Structured Log Linear Models for Noise Robust Speech Recognition S.-X. Zhang, A. Ragni, and M.J.F. Gales. To appear IEEE Signal Processing Letters.

[ Journals | Conferences | Technical Reports | Invited Talks | Home]

Thesis

M.J.F. Gales (1996). Model-Based Techniques for Noise Robust Speech Recognition.

Journal Papers

M.J.F. Gales and S.J. Young (1993).
Cepstral Parameter Compensation for HMM recognition in Noise.
Speech Communication Volume 12

M.J.F. Gales and S.J. Young (1995).
Robust Speech Recognition in Additive and Convolutional Noise using Parallel Model Combination.
Computer Speech and Language Volume 9.

M.J.F. Gales and S.J. Young (1996).
Robust Continuous Speech Recognition using Parallel Model Combination.
IEEE Transactions on Speech and Audio Processing Volume 4.
M.J.F. Gales and P.C. Woodland (1996).
Mean and Variance Adaptation within the MLLR Framework.
Computer Speech and Language Volume 10.
M.J.F. Gales (1998).
Maximum Likelihood Linear Transformations for HMM-based Speech Recognition.
Computer Speech and Language Volume 12
M.J.F. Gales (1998).
Predictive Model-Based Compensation Schemes for Robust Speech Recognition.
Speech Communication Volume 25 1998
M.J.F. Gales, K.M. Knill and S.J. Young (1999).
State-Based Gaussian Selection in Large Vocabulary Continuous Speech Recognition using HMMs.
IEEE Transactions on Speech and Audio Processing March.
M.J.F. Gales (1999).
Semi-Tied Covariance Matrices for Hidden Markov Models.
IEEE Transactions on Speech and Audio Processing, May.
M.J.F. Gales (2000).
Cluster Adaptive Training of Hidden Markov Models.
IEEE Transactions on Speech and Audio Processing.
M.J.F. Gales (2002).
Maximum Likelihood Multiple Subspace Projection Schemes for Hidden Markov Models.
IEEE Transactions on Speech and Audio Processing, February.
M.J.F. Gales (2002).
Transformation Streams and the HMM Error Model.
Computer Speech and Language (April).
S.S. Chen, E.M. Eide, M.J.F. Gales, R.A. Gopinath, D. Kanevsky and P. Olsen (2002).
Automatic Transcription of Broadcast News.
Speech Communication (May).
A-V.I. Rosti and M.J.F. Gales (2004).
Factor Analysed Hidden Markov Models for Speech Recognition.
Computer Speech and Language.
T. Hain, P.C. Woodland, G. Evermann, M.J.F. Gales, D. Povey, G. Moore, L. Wang and X. Liu (2005).
Automatic Transcription of Conversational Telephone Speech.
IEEE Transactions on Speech and Audio Processing, November 2005.
M.J.F. Gales and S.S. Airey (2006).
Product of Gaussians for Speech Recognition.
Computer Speech and Language, January 2006.
M.J.F. Gales and M.I. Layton (2006).
Training Augmented Models using SVMs.
IEICE Special Issue on Statistical Models for Speech Recognition, March 2006.
K.C. Sim and M.J.F. Gales (2006).
Minimum Phone Error Training of Precision Matrix Models.
IEEE Transactions on Speech and Audio Processing, May 2006.
K. Yu and M.J.F. Gales (2006).
Discriminative Cluster Adaptive Training.
IEEE Transactions on Audio Speech and Language Processing, September 2006.
M.J.F. Gales, D.Y. Kim , P.C. Woodland, D. Mrva, R. Sinha and S.E Tranter (2006).
Progress in the CU-HTK Broadcast News Transcription System.
IEEE Transactions on Audio Speech and Language Processing, September 2006.
X. Liu and M. J. F. Gales (2007).
Automatic Model Complexity Control Using Marginalized Discriminative Growth Functions.
IEEE Transactions on Audio, Speech and Language Processing.
M.I. Layton and M.J.F. Gales (2007).
Acoustic Modelling using Continuous Rational Kernels.
Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, August 2007.
K. Yu and M.J.F. Gales (2007).
Bayesian Adaptive Inference and Adaptive Training.
IEEE Transactions on Audio Speech and Language Processing, August.
K.C. Sim and M.J.F. Gales (2007).
Discriminative Semi-Parameteric Trajectory Models for Speech Recognition.
Computer Speech and Language, October.
H. Liao and M.J.F. Gales (2008).
Issues with Uncertainty Decoding for Noise Robust Automatic Speech Recognition.
Speech Communication, April 2008
M.J.F. Gales and S.J. Young (2008).
The Application of Hidden Markov Models in Speech Recognition.
Foundations and Trends in Signal Processing.
C. Breslin and M.J.F. Gales (2009)
Directed Decision Trees for Generating Complementary Systems
Speech Comunication May 2009
K. Yu, M.J.F. Gales and P.C. Woodland (2009).
Unsupervised Adaptation with Discriminative Mapping Transforms.
IEEE Transactions on Audio Speech and Language Processing May 2009.
C. Longworth and M.J.F. Gales (2009).
Combining Derivative and Parametric Kernels for Speaker Verification.
IEEE Transactions on Audio Speech and Language Processing May 2009

top

Selected Conference Papers

M.J.F. Gales D. Pye and P.C. Woodland (1996).
Variance Compensation within the MLLR Framework for Robust Speech Recognition and Speaker Adaptation.
ICSLP 1996.
M.J.F. Gales (1997).
Transformation Smoothing for Speaker and Environmental Adaptation.
Eurospeech 1997.
H.J Nock, M.J.F. Gales and S.J. Young(1997).
A Comparative Study of Methods for Phonetic Decision-Tree Clustering.
Eurospeech 1997.
M.J.F. Gales and P.A. Olsen (1999).
Tail Distribution Modelling Using the Richter and Power Exponential Distributions.
Eurospeech 1999.
A. Aiyer, M.J.F. Gales and M.A. Picheny (2000).
Rapid Likelihood Calculation of Subspace Clustered Gaussian Components.
ICASSP2000.
M.J.F. Gales (2000).
Factored Semi-Tied Covariance Matrices.
NIPS 2000.
M.J.F. Gales (2001).
Multiple-Cluster Adaptive Training Schemes.
ICASSP 2001.
M.N. Stuttle and M.J.F. Gales (2001).
A Mixture of Gaussians Front End for Speech Recognition.
Eurospeech 2001.
N. Smith and M.J.F. Gales (2001).
Speech Recognition using SVMs.
NIPS 2001.
M.J.F. Gales (2001).
Acoustic Factorisation.
ASRU 2001.
M.J.F. Gales (2002).
The HMM Error Model.
ICASSP 2002.
R. Cordoba, P.C. Woodland and M.J.F. Gales (2002).
Improving Cross Task Performance Using MMI Training.
ICASSP 2002.
A-V.I. Rosti and M.J.F. Gales (2002).
Factor Analysed HMMs.
ICASSP 2002.
N.D. Smith and M.J.F. Gales (2002).
SVMs for Speech Recognition.
ICASSP 2002.
M.N. Stuttle and M.J.F. Gales (2002).
Combining a Gaussian Mixture Model Frontend with MFCC Parameters.
ICSLP 2002.
S.S. Airey and M.J.F. Gales (2003).
Product of Gaussians and Multiple Stream Systems.
ICASSP 2003.
X. Liu, M.J.F. Gales and P.C. Woodland (2003).
Automatic Complexity Control for HLDA Systems.
ICASSP 2003.
D. Povey, P.C. Woodland and M.J.F. Gales (2003).
Discriminative MAP for Acoustic Model Adaptation.
ICASSP 2003.
M.J.F. Gales, Y. Dong, D. Povey and P.C. Woodland (2003).
Porting: SwitchBoard to the VoiceMail Task.
ICASSP 2003.
D. Povey, M.J.F. Gales, D.Y. Kim and P.C. Woodland (2003).
MMI-MAP and MPE-MAP for Acoustic Model Adaptation.
EuroSpeech 2003.
S.S. Airey and M.J.F. Gales (2003).
Product of Gaussians as a Distributed Representation for Speech Recognition.
EuroSpeech 2003.
X. Liu and M.J.F. Gales (2003).
Automatic Model Complexity Control Using Marginalised Discriminative Growth Functions.
ASRU 2003.
X. Liu and M.J.F. Gales (2004).
Automatic Model Complexity Control and Compression Using Discriminative Growth Functions.
ICASSP04.
K. Yu and M.J.F. Gales (2004).
Adaptive Training using Structured Transforms.
ICASSP04.
A-V.I. Rosti and M.J.F. Gales (2004).
Rao-Blackwellised Gibbs Sampling for Switching Linear Dynamical Systems.
ICASSP04.
K.C. Sim and M.J.F. Gales (2004).
Basis Superposition Precision Matrix Models for Large Vocabulary Continuous Speech Recognition.
ICASSP04.
G. Evermann, H.Y. Chan, M.J.F. Gales, T. Hain, X. Liu, D. Mrva, L. Wang and P.C. Woodland (2004).
Development of the 2003 CU-HTK Conversational Telephone Speech Transcription System.
ICASSP04.
G. Evermann, H.Y. Chan, M.J.F. Gales, T. Hain, X. Liu, D. Mrva, L. Wang and P.C. Woodland (2004).
Development of the 2003 CU-HTK Conversational Telephone Speech Transcription System.
ICASSP04.
D.Y. Kim, S. Umesh, M.J.F. Gales, T. Hain and P.C. Woodland (2004).
Using VTLN for Broadcast News Transcription.
ICSLP04.
K.C. Sim and M.J.F. Gales (2005).
Adaptation of Precision Matrix Models on LVCSR.
ICASSP05.
D.Y. Kim, H.Y. Chan,G. Evermann, M.J.F. Gales, D. Mrva, K.C. Sim and P.C. Woodland (2005).
Development of the CU-HTK 2004 Broadcast News Transcription Systems.
ICASSP05.
X. Liu, M.J.F. Gales, K.C. Sim and K. Yu (2005).
Investigation of Acoustic Modelling Techniques for LVCSR Systems.
ICASSP05.
G. Evermann, M.J.F. Gales, B. Jia, D. Mrva, P.C. Woodland and K. Yu (2005).
Training LVCSR Systems on Thousands of Hours of Data.
ICASSP05.
M.J.F. Gales, B. Jia X. Liu, K.C. Sim P.C. Woodland and K. Yu (2005).
Development of the CUHTK 2004 Mandarin Conversational Telephone Speech Transcription System.
ICASSP05.
K.C. Sim and M.J.F. Gales (2005).
Temporally Varying Model Parameters for LVCSR.
InterSpeech 2005.
H. Liao and M.J.F. Gales (2005).
Joint Uncertainty Decoding for Noise Robust Speech Recognition.
InterSpeech 2005.
R. Sinha, S. Tranter, M.J.F. Gales and P.C. Woodland (2005).
The Cambridge University March 2005 Speaker Diarisation System.
InterSpeech 2005.
K. Yu and M.J.F. Gales (2005).
Bayesian adaptation and adaptively trained systems.
ASRU 2005
R. Sinha, M.J.F. Gales D.Y. Kim, X.A. Liu K.C. Sim and P.C. Woodland (2006).
The CU-HTK Mandarin Broadcast New Transcription System.
ICASSP 2006.
M.I. Layton and M.J.F. Gales (2006).
Augmented Statistical Models for Speech Recognition.
ICASSP 2006
K. Yu and M.J.F. Gales (2006).
Incremental Bayesian Adaptation.
ICASSP 2006
H. Liao and M.J.F. Gales (2006).
Issues with Uncertainty Decoding for Noise Robust Speech Recognition.
InterSpeech 2006.
C. Breslin and M.J.F. Gales (2006).
Generating Complementary Systems for Speech Recognition.
InterSpeech 2006.
C. Longworth and M.J.F. Gales (2006).
Discriminative Adaptation for Speaker Verification.
InterSpeech 2006.
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 (2007).
Speech Recognition System Combination for Machine Translation.
ICASSP 2007.
L. Wang, M.J.F. Gales and P.C. Woodland (2007).
Unsupervised Training for Mandarin Broadcast News and Conversation Transcription.
ICASSP 2007.
H. Liao and M.J.F. Gales (2007).
Adaptive Training with Joint Uncertainty Decoding for Robust Recognition of Noisy Data.
ICASSP 2007.
K. Yu, M. J. F. Gales and P. C. Woodland. (2007)
Unsupervised training with directed manual transcription for recognizing Mandarin broadcast audio.
InterSpeech 2007
C. Longworth and M. J. F. Gales. (2007)
Derivative and Parametric Kernels for Speaker Verification.
InterSpeech 2007
C. Breslin and M.J.F. Gales (2007).
Building Multiple Complementary Systems using Directed Decision Trees.
InterSpeech 2007.
X. Liu, W. Byrne, M. J. F. Gales, A. Gispert, M. Tomalin, P. C. Woodland and K. Yu. (2007)
Discriminative language model adaptation for Mandarin broadcast speech transcription and translation.
ASRU 2007
M. J. F. Gales, F. Diehl, C. K. Raut, M. Tomalin, P. C. Woodland and K. Yu. (2007)
Development of a phonetic system for large vocabulary Arabic speech recognition.
ASRU 2007
M.J.F. Gales and R.C. van Dalen (2007).
Predictive Linear Transforms for Noise Robust Speech Recognition.
ASRU 2007.
K. Yu, M.J.F Gales. P.C. and Woodland (2008)
Unsupervised Discriminative Adaptation using Discriminative Mapping Transforms
ICASSP 2008.
F. Diehl, M.J.F. Gales, M. Tomalin and P.C. Woodland (2008)
Phonetic Pronunciations for Arabic Speech-to-Test Systems
ICASSP 2008.
C. Longworth and M.J.F. Gales (2008)
Multiple Kernel Learning for Speaker Verification
ICASSP 2008.
M.J.F. Gales and C. Longworth (2008)
Discriminative Classifiers with Generative Kernels for Noise Robust ASR.
InterSpeech 2008.
R.C. van Dalen and M.J.F. Gales (2008)
Covariance Modelling for Noise-Robust Speech Recognition.
InterSpeech 2008.
C.K. Raut K., Yu and M.J.F. Gales (2008)
Adaptive Training using Discriminative Mapping Transforms
InterSpeech 2008.
X. Liu, M.J.F. Gales and P.C. Woodland (2008)
Context Dependent Language Model Adaptation
InterSpeech 2008.
C. Longworth and M.J.F. Gales (2008)
A Generalised Derivative Kernel for Speaker Verification
InterSpeech 2008.

top

Selected Technical Reports

M.J.F. Gales and S.J. Young (1993).
The Theory of Segmental Hidden Markov Models.
Technical Report CUED/F-INFENG/TR.133 June 1993.
M.J.F. Gales (1996).
The Generation and Use of Regression Class Trees for MLLR Adaptation.
Technical Report CUED/F-INFENG/TR.263 August 1996.
M.J.F. Gales (1997).
Adapting Semi-Tied Full-Covariance Matrix HMMs.
Technical Report CUED/F-INFENG/TR.298 July 1997.
M.J.F. Gales (1999).
Maximum Likelihood Multiple Projection Schemes for Hidden Markov Models.
Technical Report CUED/F-INFENG/TR.365 October 1999 (Revised June 2000).
M.J.F. Gales (2001).
Transformation Streams and the HMM Error Model.
Technical Report CUED/F-INFENG/TR.416 July 2001.
A-V.I. Rosti and M.J.F. Gales (2001).
Generalised Linear Gaussian Models.
Technical Report CUED/F-INFENG/TR.420 October 2001.
N.D. Smith and M.J.F. Gales (2002).
Using SVMs to Classify Variable Length Speech Patterns.
Technical Report CUED/F-INFENG/TR.412 April 2002 (Revised version).
A-V.I. Rosti and M.J.F. Gales (2003).
Factor Analysed Hidden Markov Models for Speech Recognition.
Technical Report CUED/F-INFENG/TR.453 April 2003.
M.J.F. Gales and S.S. Airey(2003).
Product of Gaussians for Speech Recognition.
Technical Report CUED/F-INFENG/TR.458 May 2003.
A-V.I. Rosti and M.J.F. Gales (2003).
Switching Linear Dynamical Systems for Speech Recognition .
Technical Report CUED/F-INFENG/TR.461 December 2003.
T. Hain, P.C. Woodland, G. Evermann, M.J.F. Gales, X. Liu, G.L. Moore, D. Povey & L. Wang(2003),
Automatic Transcription of Conversational Telephone Speech - Development of the CU-HTK 2002 System
Technical report CUED/F-INFENG/TR.465.
M.I. Layton and M.J.F. Gales (2004).
Maximum Margin Training of Generative Kernels.
Technical Report CUED/F-INFENG/TR.484 June 2004.
K.C. Sim and M.J.F. Gales (2004).
Precision Matrix Modelling for Large Vocabulary Continuous Speech Recognition .
Technical Report CUED/F-INFENG/TR.485 June 2004.
K. Yu and M.J.F. Gales (2004).
Discriminative Cluster Adaptive Training .
Technical Report CUED/F-INFENG/TR.486 June 2004.
H.. Liao and M.J.F. Gales (2004).
Uncertainty Decoding for Noise Robust Automatic Speech Recogntion .
Technical Report CUED/F-INFENG/TR.499 October 2004.
M.J.F. Gales, B. Jia, X. Liu, K.C. Sim, P.C. Woodland and K. Yu (2004).
Development of the CUHTK 2004 RT04F Mandarin Conversational Telephone Speech Transcription System .
RT04f Workshop November 2004.
H. Liao and M.J.F. Gales (2006).
Joint Uncertainty Decoding for Robust Large Vocabulary Speech Recognition.
Technical Report CUED/F-INFENG/TR.552 November 2006.
M.J.F. Gales and F. Flego (2008).
Discriminative Classifiers and Generative Kernels for Noise Robust Speech Recognition.
Technical Report CUED/F-INFENG/TR.605 August 2008.
D.K. Kim and M.J.F. Gales (2009).
Noisy CMLLR for Noise-Robust Speech Recognition.
CUED Technical Report CUED/F-INFENG/TR611, February 2009.

top

Selected Invited Talks

M.J.F. Gales (1997).
"Nice" Model-Based Compensation Schemes for Robust Speech Recognition.
1997 ECSA/NATO Tutorial and Research Workshop on Robust speech recognition for unknown communication channels.
M.J.F. Gales (1998).
Constrained Estimation of Hidden Markov Models.
1998 NSF Language Engineering Workshop at Johns Hopkins University, Baltimore.
M.J.F. Gales (2000).
Linear Transformations (Yet Again!!).
IBM T.J. Watson Research Center.
M.J.F. Gales (2001).
Adaptive Training Schemes for Robust ASR.
ASRU 2001.
Associated paper Adaptive Training for Robust ASR ASRU 2001 proceedings.
M.J.F. Gales (2004).
Machine Learning for Speech and Language Processing.
Foresight Cognitive Systems Workshop.
M.J.F. Gales and M. Layton (2004).
SVMs, Generative Kernels and Maximum Margin Statistical Models.
Institute of Statistical Mathematics, Tokyo.
A related invited paper presented at the Beyond HMM Workshop 2004, ATR, is also available.
M.J.F. Gales and M. Layton (2005).
Augmented Statistical Models for Speech Recognition.
Trajectory Models for Speech Processing Workshop, Edinburgh
M.J.F. Gales and P.C. Woodland (2006).
Recent advances in large vocabulary continuous speech recognition: An HTK perspective.
ICASSP 2006 Tutorial, Toulouse, France.
M.J.F. Gales (2006).
Complementary System Combination and Generation for ASR .
TC-Star Speech-to-Speech Translation Workshop, UPC, Spain.
M.J.F. Gales (2006).
Modelling Dependencies in Sequence Data Classification.
University of East Anglia
M.J.F. Gales (2007).
Discriminative Models for Speech Recognition.
Information Theory and Applications Workshop, UCSD, California, USA.
A related invited paper is also available. An extended version of this paper (revised May 2007), which includes a longer discussion of large margin training of HMMs and some typo corrections, is also available.
M.J.F. Gales (2008).
Model-Based Approaches to Robust Speech Recognition .
King's College London.
M.J.F. Gales (2008).
Instantaneous and Discriminative Adaptation for Automatic Speech Recognition .
August 2008
M.J.F. Gales (2008).
Model-Based Approaches to Robust Speech Recognition .
Edinburgh University
M.J.F. Gales (2009).
Model-Based Approaches to Speaker and Environment Adaptation .
Tsinghua University, Beijing
M.J.F. Gales (2009).
Sequence Kernels for Speaker and Speech Recognition.
Language Techniology Workshop at Johns Hopkins University, Baltimore.
M.J.F. Gales (2009).
Acoustic Modelling for Speech Recognition: Hidden Markov Models and Beyond?.
ASRU 2009.

top

[ Cambridge University | CUED | MIL | Home]