Gales, Mark - Machine Intelligence Laboratory, Department of Engineering, University of Cambridge

• DEVELOPMENT OF THE CUHTK 2004 MANDARIN CONVERSATIONAL TELEPHONE SPEECH TRANSCRIPTION SYSTEM
• MORTGAGE DEFAULT: CLASSIFICATION TREES ANALYSIS
• Minimax Probability Machine Gert R.G. Lanckriet \Lambda
• Extended MLLT for Gaussian Mixture Models Peder A. Olsen and Ramesh A. Gopinath
• University of Cambridge MPhil in Computer Speech & Language
• TAIL DISTRIBUTION MODELLING USING THE RICHTER AND POWER EXPONENTIAL DISTRIBUTIONS
• TAIL DISTRIBUTION MODELLING USING THE RICHTER AND POWER EXPONENTIAL DISTRIBUTIONS
• Investigations on Discriminative Training Criteria Von der Fakultat Mathematik, Informatik
• University of Cambridge Engineering Part IIB
• Engineering Tripos Part IIB FOURTH YEAR Paper 4F10: Statistical Pattern Processing
• Publications Thesis, Books and Book Chapters
• Speech Recognition using SVMs Nathan Smith
• Discriminative Semi-parametric Trajectory Model for Speech Recognition
• Discriminative Classifiers with Generative Kernels for Noise Robust ASR M.J.F. Gales and C. Longworth
• A Mixture of Gaussians Front End for Speech Recognition M.N. Stuttle and M.J.F. Gales
• RAPID LIKELIHOOD CALCULATION OF SUBSPACE CLUSTERED GAUSSIAN COMPONENTS
• Structured Precision Matrix Modelling for Speech Recognition
• Model-Based Approaches to Speaker and Environment Adaptation
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• A Comparison of Methods for Multi-class Support Vector Machines
• Hynek Hermansky, "Should Recognizers Have Ears?," in Proc. ESCA Tutorial and Research Workshop on Robust Speech Recognition for Unknown Communication Channels, pp. 110, France 1997.
• University of Cambridge MPhil in Computer Speech & Language
• Speaker Adaptation for Continuous Density HMMs: A Review P.C. Woodland
• STRUCTURED DISCRIMINATIVE MODELS FOR NOISE ROBUST CONTINUOUS SPEECH RECOGNITION
• BASIS SUPERPOSITION PRECISION MATRIX MODELS FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
• Joint Uncertainty Decoding for Noise Robust Speech Recognition H. Liao and M. J. F. Gales
• University of Cambridge Engineering Part IIB
• Transformations ENGINEERING
• STATEBASED GAUSSIAN SELECTION IN LARGE VOCABULARY CONTINUOUS SPEECH
• Engineering Eurospeech'03
• Gaussian Process Regression 4F10 Pattern Recognition, 2010
• DISCRIMINATIVE LANGUAGE MODEL ADAPTATION FOR MANDARIN BROADCAST SPEECH TRANSCRIPTION AND TRANSLATION
• Covariance Modelling for Noise-Robust Speech Recognition R. C. van Dalen, M. J. F. Gales
• University of Cambridge Engineering Part IIB
• Discriminative Adaptive Training and Bayesian Inference for
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• ADAPTIVE TRAINING FOR ROBUST ASR M.J.F. Gales
• Augmented Statistical Models for Classifying Sequence Data
• MULTIPLE KERNEL LEARNING FOR SPEAKER VERIFICATION C. Longworth and M.J.F. Gales
• AUTOMATIC COMPLEXITY CONTROL FOR HLDA SYSTEMS X. Liu, M. J. F. Gales and P. C. Woodland
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Porting: SwitchBoard to the VoiceMail Task M.J.F. Gales, Y. Dong, D. Povey & P.C. Woodland
• MULTIPLECLUSTER ADAPTIVE TRAINING SCHEMES M.J.F. Gales
• Augmented Statistical Models for Classifying Sequence Data
• THE CU-HTK MANDARIN BROADCAST NEWS TRANSCRIPTION SYSTEM R. Sinha, M.J.F. Gales, D.Y. Kim
• PRODUCT OF GAUSSIANS AND MULTIPLE STREAM SYSTEMS S.S. Airey and M.J.F. Gales
• Engineering recognition
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Temporally Varying Model Parameters for Large Vocabulary Continuous Speech Recognition
• IMPROVED CROSSTASK RECOGNITION USING MMIE TRAINING R. C ordoba , P.C. Woodland & M.J.F. Gales
• FACTOR ANALYSED HIDDEN MARKOV MODELS AV.I. Rosti and M.J.F. Gales
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Acoustic Modelling for Speech Recognition: Hidden Markov Models and Beyond?
• IEICE TRANS. ??, VOL.Exx??, NO.xx XXXX 200x INVITED PAPER
• Speech-Driven Cartoon Animation with Emotions Yan Li, Feng Yu* Ying-Qing Xu, Eric Chang, Heung-Yeung Shum
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• University of Cambridge Engineering Part IIB
• Precision and Covariance Matrix Modelling Khe Chai Sim & Mark Gales
• MMIMAP and MPEMAP for Acoustic Model Adaptation D. Povey, M.J.F. Gales, D.Y. Kim, & P.C. Woodland
• SVMs, Generative Kernels & Maximum Margin Statistical Models
• University of Cambridge Engineering Part IIB
• DEVELOPMENT OF THE CUHTK 2004 RT04F MANDARIN CONVERSATIONAL TELEPHONE SPEECH TRANSCRIPTION SYSTEM
• THE HMM ERROR MODEL Cambridge University Engineering Department
• ModelBased Compensation
• discriminative recognition
• MODEL-BASED TECHNIQUES FOR NOISE ROBUST SPEECH RECOGNITION
• DEVELOPMENT OF A PHONETIC SYSTEM FOR LARGE VOCABULARY ARABIC SPEECH RECOGNITION
• Product of Gaussians for Speech Recognition M.J.F. Gales and S.S. Airey
• Adaptive Training using Discriminative Mapping Transforms C. K. Raut, K. Yu and M. J. F. Gales
• Factor analysed hidden Markov models for speech recognition
• JOURNAL OF IEEE TRANS. ACOUST., SPEECH, SIGNAL PROCESSING, JULY 2006 1 Minimum Phone Error Training of Precision Matrix
• IEEE TRANS. ON SAP, VOL. ?, NO. ??, ????? 2006 1 Bayesian Adaptive Inference and Adaptive Training
• BAYESIAN ADAPTATION AND ADAPTIVELY TRAINED SYSTEMS K. Yu and M.J.F. Gales
• Explicitly Generating Complementary Systems for Large Vocabulary Continuous Speech Recognition
• Derivative and Parametric Kernels for Speaker Verification C. Longworth and M.J.F. Gales
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Model-Based Approaches to Robust Speech Recognition
• Instantaneous and Discriminative Adaptation for Automatic Speech Recognition
• Model-Based Approaches to Robust Speech Recognition
• Generation and Combination of Complementary Systems for
• Discriminative Complexity Control and Linear Projections for Large
• Model-Based Approaches to Handling Uncertainty
• Foundations and Trends R Signal Processing
• A Gaussian Mixture Model Spectral Representation for
• Adaptive Training for Large Vocabulary Continuous
• University of Cambridge Engineering Part IIB
• Engineering Tripos Part IIB FOURTH YEAR Module 4F10: STATISTICAL PATTERN RECOGNITION
• Structured Log Linear Models for Noise Robust Speech Recognition
• IEEE TRANS. ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007 1 Progress in the CU-HTK Broadcast News
• IEEE TRANS. ON SAP, VOL. ?, NO. ??, ????? 200? 1 Automatic Model Complexity Control Using
• Journal of VLSI Signal Processing manuscript No. (will be inserted by the editor)
• Issues with Uncertainty Decoding for Noise Robust Speech Recognition
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Augmented Statistical Models for Speech Recognition
• Complementary System Combination and Generation for ASR
• Discriminative Models for Speech Recognition M.J.F. Gales
• University of Cambridge Engineering Part IIB
• University of Cambridge Engineering Part IIB
• University of Cambridge Engineering Part IIB
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• INCREMENTAL BAYESIAN ADAPTATION K. Yu and M.J.F. Gales
• The Lumiere Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users
• DISCRIMINATIVE CLASSIFIERS WITH ADAPTIVE KERNELS FOR NOISE
• Linear Gaussian Models for Speech Recognition
• CU-HTK Mandarin CTS System September 2003
• Product of Gaussians & Multiple Stream Systems Sarah Airey & Mark Gales
• ROBUST CONTINUOUS SPEECH RECOGNITION USING PARALLEL MODEL COMBINATION
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• RAOBLACKWELLISED GIBBS SAMPLING FOR SWITCHING LINEAR DYNAMICAL AV.I. Rosti and M.J.F. Gales
• COMBINING A GAUSSIAN MIXTURE MODEL FRONT END WITH MFCC PARAMETERS M.N. Stuttle and M.J.F. Gales
• DEVELOPMENT OF THE 2003 CUHTK CONVERSATIONAL TELEPHONE SPEECH TRANSCRIPTION SYSTEM
• M. J. F. Gales & S. J. Young Cambridge University Engineering Department
• ACOUSTIC FACTORISATION M.J.F. Gales
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• mjfg@eng.cam.ac.uk ENGINEERING
• Product of Gaussians as a Distributed Representation for Speech Recognition S.S. Airey and M.J.F. Gales
• Recent Progress in Large Vocabulary Continuous Speech Recognition: An HTK Perspective
• University of Cambridge Engineering Part IIB
• SPEECH RECOGNITION SYSTEM COMBINATION FOR MACHINE TRANSLATION M.J.F. Gales
• Constrained mjfg@watson.ibm.com
• MAXIMUM LIKELIHOOD LINEAR TRANSFORMATIONS FOR HMMBASED
• DISCRIMINATIVE MAP FOR ACOUSTIC MODEL ADAPTATION D. Povey, P.C. Woodland & M.J.F. Gales
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• PORTING: SWITCHBOARD TO THE VOICEMAIL TASK M.J.F. Gales, Y. Dong, D. Povey and P.C. Woodland
• AUGMENTED STATISTICAL MODELS FOR SPEECH RECOGNITION M.I. Layton and M.J.F. Gales
• Discriminative Models for Speech Recognition M.J.F. Gales
• Support Vector Machines for Noise Robust ASR M. J. F. Gales, A. Ragni, H. AlDamarki and C. Gautier
• Building Multiple Complementary Systems using Directed Decision Trees C. Breslin and M.J.F. Gales
• Discriminative Linear Transforms for Speaker Adaptation L.F. Uebel & P.C. Woodland
• MINIMUM PHONE ERROR AND I-SMOOTHING FOR IMPROVED DISCRIMINATIVE TRAINING
• Discriminative Models for Speech Recognition 1 February 2007
• TRANSFORMATION SMOOTHING FOR SPEAKER AND ENVIRONMENTAL ADAPTATION
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• USING SVMS AND DISCRIMINATIVE MODELS FOR SPEECH RECOGNITION N.D. Smith and M.J.F. Gales
• University of Cambridge Engineering Part IIB
• University of Cambridge Engineering Part IIB
• Discriminative Adaptation for Speaker Verification C. Longworth and M. J. F. Gales
• UNSUPERVISED TRAINING FOR MANDARIN BROADCAST NEWS AND CONVERSATION TRANSCRIPTION
• PREDICTIVE LINEAR TRANSFORMS FOR NOISE ROBUST SPEECH RECOGNITION M.J.F. Gales and R.C. van Dalen
• ADAPTIVE TRAINING WITH JOINT UNCERTAINTY DECODING FOR ROBUST RECOGNITION OF NOISY DATA
• Kernel Methods for Text-Independent
• SVMS, SCORE-SPACES AND MAXIMUM MARGIN STATISTICAL MODELS M.J.F. Gales and M. Layton
• DISCRIMINATIVE CLASSIFIERS WITH ADAPTIVE KERNELS FOR NOISE
• Uncertainty Decoding for Noise Robust Speech Recognition
• Multiple-Cluster mjfg@eng.cam.ac.uk
• Mean and Variance Adaptation within the MLLR Framework
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Machine Learning for Speech & Language 28 June 2004
• THE HMM ERROR MODEL M.J.F. Gales
• ADAPTIVE TRAINING USING STRUCTURED TRANSFORMS K. Yu and M.J.F. Gales
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• Automatic Transcription of Broadcast News S. S. Chen, E. Eide, M. J. F. Gales, R. A. Gopinath, D. Kanvesky and P. Olsen
• PREDICTIVE MODELBASED COMPENSATION SCHEMES FOR ROBUST SPEECH RECOGNITION
• FACTOR ANALYSED HIDDEN MARKOV MODELS
• Engineering http://svrwww.eng.cam.ac.uk/mns25
• BAYESIAN COMPRESSIVE SENSING FOR PHONETIC CLASSIFICATION Tara N. Sainath1
• Sequence Kernels for Speaker and Speech Recognition
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• AUTOMATIC MODEL COMPLEXITY CONTROL USING MARGINALIZED DISCRIMINATIVE GROWTH FUNCTIONS
• Context Dependent Language Model Adaptation X. Liu, M. J. F. Gales & P. C. Woodland
• IEEE TRANS. ON ASL, VOL. ?, NO. ??, ????? 2008 1 Unsupervised Adaptation with Discriminative
• A Generalised Derivative Kernel for Speaker Verification C. Longworth and M.J.F. Gales
• Modelling Dependencies in Sequence Classification: Augmented Statistical Models
• BOOSTING GAUSSIAN MIXTURES IN AN LVCSR SYSTEM Geo rey Zweig and Mukund Padmanabhan
• CAMBRIDGE UNIVERSITY ENGINEERING DEPARTMENT
• VARIANCE COMPENSATION WITHIN THE MLLR FRAMEWORK FOR ROBUST SPEECH RECOGNITION AND SPEAKER ADAPTATION
• MODEL COMPLEXITY CONTROL AND COMPRESSION USING DISCRIMINATIVE GROWTH FUNCTIONS
• Factored SemiTied Covariance Matrices M.J.F. Gales
• IEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING, VOL. 6, NO. 1, JANUARY 2007 1 Combining Derivative and Parametric Kernels for
• Statistical Models for Noise-Robust
• 3F3: Signal and Pattern Processing Lecture 2: Regression
• A Variational Perspective on Noise-Robust Speech Recognition
• Extending Noise Robust Structured Support Vector Machines to Larger Vocabulary Tasks
• IEEE SIGNAL PROCESSING LETTERS 1 Kernel Eigenvoices (Revisited) for
• Structured Support Vector Machines for Noise Robust Continuous Speech Recognition
• 3F3: Signal and Pattern Processing Lecture 1: Introduction
• Morphological Decomposition in Arabic ASR Systems
• 3F3: Signal and Pattern Processing Lecture 5: Dimensionality Reduction
• IEEE TRANSACTIONS ON AUDIO, SPEECH, & LANGUAGE PROCESSING, VOL. X, NO. X, JANUARY 2011 1 Statistical Parametric Speech Synthesis Based on
• Derivative Kernels for Noise Robust ASR A. Ragni and M. J. F. Gales
• SPECIAL ISSUE ON FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION 1 Structured Discriminative Models
• Improving Reverberant VTS for Hands-free Robust Speech Recognition
• 3F3: Signal and Pattern Processing Lecture 4: Clustering
• Model-Based Approaches to Handling Uncertainty
• IEEE TRANSACTIONS ON AUDIO, SPEECH, & LANGUAGE PROCESSING, VOL. X, NO. X, JANUARY 2011 1 Product of Experts for Statistical Parametric
• 3F3: Signal and Pattern Processing Lecture 3: Classification