M. Gales

发表

Mean and variance adaptation within the MLLR framework

Mark J. F. Gales, Philip C. Woodland, P. Woodland, 1996, Comput. Speech Lang..

Semi-tied Full-covariance Matrices for Hidden Markov Models

M. Gales, 1997 .

Semi-tied covariance matrices for hidden Markov models

Mark J. F. Gales, M. Gales, 1999, IEEE Trans. Speech Audio Process..

Maximum likelihood linear transformations for HMM-based speech recognition

Mark J. F. Gales, M. Gales, 1998, Comput. Speech Lang..

Product of Experts for Statistical Parametric Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

The HTK book version 3.4

Steve Young, Gunnar Evermann, Daniel Povey, 2006 .

Integrated Online Speaker Clustering and Adaptation

Mark J. F. Gales, Kate Knill, K. K. Chin, 2011, INTERSPEECH.

The Cu-Htk Mandarin Broadcast News Transcription System

Mark J. F. Gales, Xunying Liu, Khe Chai Sim, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Speech Recognition using SVMs

Mark J. F. Gales, N. Smith, M. Gales, 2001, NIPS.

Multiple-cluster adaptive training schemes

Mark J. F. Gales, M. Gales, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Derivative kernels for noise robust ASR

Mark J. F. Gales, Anton Ragni, M. Gales, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

The Application of Hidden Markov Models in Speech Recognition

Mark J. F. Gales, Steve J. Young, S. Young, 2007, Found. Trends Signal Process..

DEVELOPMENT OF THE CUHTK 2004 RT 04 F MANDARIN CONVERSATIONAL TELEPHONE SPEECH TRANSCRIPTION SYSTEM

P. Woodland, M. Gales, K. Yu, 2004 .

Variance compensation within the MLLR framework

Mark J. F. Gales, Philip C. Woodland, P. Woodland, 1996 .

MMI-MAP and MPE-MAP for acoustic model adaptation

Mark J. F. Gales, Daniel Povey, Philip C. Woodland, 2003, INTERSPEECH.

Model-based techniques for noise robust speech recognition

Mark J. F. Gales, M. Gales, 1995 .

Efficient lattice rescoring using recurrent neural network language models

Yongqiang Wang, Mark J. F. Gales, Xunying Liu, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition

Yongqiang Wang, Mark J. F. Gales, Xunying Liu, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Robust excitation-based features for Automatic Speech Recognition

Mark J. F. Gales, Yannis Stylianou, Thomas Drugman, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models

Yongqiang Wang, Mark J. F. Gales, Xunying Liu, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Adaptive Training with Joint Uncertainty Decoding for Robust Recognition of Noisy Data

Mark J. F. Gales, Hank Liao, M. Gales, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Broadcast news transcription using HTK

Mark J. F. Gales, Steve J. Young, Philip C. Woodland, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Progress in the CU-HTK broadcast news transcription system

Mark J. F. Gales, Ricky Ho Yin Chan, Philip C. Woodland, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

Lightly supervised recognition for automatic alignment of large coherent speech recordings

Mark J. F. Gales, Sabine Buchholz, Norbert Braunschweiler, 2010, INTERSPEECH.

Predictive Uncertainty Estimation via Prior Networks

Mark J. F. Gales, Andrey Malinin, M. Gales, 2018, NeurIPS.

Iterative unsupervised adaptation using maximum likelihood linear regression

Mark J. F. Gales, Philip C. Woodland, David Pye, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

Multiple kernel learning for speaker verification

Mark J. F. Gales, Chris Longworth, M. Gales, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization

Heiga Zen, Sacha Krstulovic, Mark J. F. Gales, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

Uncertainty in Structured Prediction

M. Gales, A. Malinin, 2020, ArXiv.

Deliberation-Based Multi-Pass Speech Synthesis

M. Gales, M. Wan, Qing Dou, 2021, Interspeech.

Improving lightly supervised training for broadcast transcription

Mark J. F. Gales, Yanhua Long, Pierre Lanchantin, 2013, INTERSPEECH.

Confidence Scores for Speech Processing

M. Gales, Qiujia Li, 2018 .

INCREMENTAL BAYESIAN ADAPTATION

M. Gales, K. Yu, 2022 .

Acoustic Modelling Using Continuous Rational Kernels

M. Gales, M. Layton, 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

RECURRENT NEURAL NETWORK LANGUAGE MODELS FOR KEYWORD SEARC

M. Gales, X. Liu, K. Knill, 2016 .

Recurrent neural network language model training with noise contrastive estimation for speech recognition

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Maximum likelihood multiple projection schemes for hidden Markov models

Mark J. F. Gales, M. Gales, 1999 .

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks pdf

Mark J. F. Gales, Andrey Malinin, Alexey Noskov, 2021, ArXiv.

Using SVMs to classify variable length speech patterns

Mark J. F. Gales, Nd Smith, M. Gales, 2002 .

Grade Feature extraction Speech recogniser Text Features Grader Error Detection & Correction

M. Gales, K. Kyriakopoulos, K. Knill, 2017 .

Ensemble Methods and Efficient Decoding

M. Gales, J. H. M. Wong, 2016 .

Generating Complementary Systems for Large Vocabulary Continuous Speech Recognition

M. Gales, C. Breslin, 2022 .

Light Supervised Data Selection, Voice Quality Normalized Training and Log Domain Pulse Synthesis

M. Gales, P. Lanchantin, G. Degottex, 2017 .

Generative Kernels and Score-Spaces for Classi cation of Speech : Progress Report iii

M. Gales, R. V. Dalen, J. Yang, 2012 .

Towards automatic assessment of spontaneous spoken English

Yu Wang, Mark J. F. Gales, Kate Knill, 2018, Speech Commun..

The theory of segmental hidden Markov models

Mark J. F. Gales, Steve Young, Mark J. F. Gales, 1993 .

Robust speech recognition in noise --- performance of the IBM continuous speech recogniser on the ARPA noise spoke task

Michael Picheny, Ponani S. Gopalakrishnan, Mark J. F. Gales, 1995 .

Engineering Department Noisy Cmllr for Noise-robust Speech Recognition

M. Gales, 2022 .

HMM recognition in noise using parallel model combination

Mark J. F. Gales, Steve J. Young, S. Young, 1993, EUROSPEECH.

Increasing Context for Estimating Confidence Scores in Automatic Speech Recognition

M. Gales, K. Knill, A. Ragni, 2022, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Answer Uncertainty and Unanswerability in Multiple-Choice Machine Reading Comprehension

M. Gales, Vatsal Raina, 2022, FINDINGS.

Segmental hidden Markov models

Mark J. F. Gales, Steve J. Young, S. Young, 1993, EUROSPEECH.

Shifts 2.0: Extending The Dataset of Real Distributional Shifts

M. Gales, C. Granziera, K. Kyriakopoulos, 2022, ArXiv.

Transformation Techniques in Speaker Adaptation 33 Maximum Likelihood Linear Regression 43

M. Gales, P C Woodland, 2022 .

Full-covariance model compensation for noise-robust speech recognition

Mark J. F. Gales, Rogier C. van Dalen, M. Gales, 2008 .

Non-Native Children's Automatic Speech Recognition: The INTERSPEECH 2020 Shared Task ALTA Systems

Mark J. F. Gales, Kate Knill, Yu Wang, 2020, INTERSPEECH.

Audio Grade Feature extraction Speech recogniser Text Features

M. Gales, K. Kyriakopoulos, K. Knill, 2017 .

Mandarin Chinese LVCSR System for Speech Translation

P. Woodland, M. Gales, Xunying Liu, 2015 .

The generation and use of regression class trees for MLLR adaptation

Mark J. F. Gales, M. Gales, 1996 .

Recent Progress in Large Vocabulary Continuous Speech Recognition: An HTK Perspective

Mark J. F. Gales, Philip C. Woodland, P. Woodland, 2006 .

Parallel model combination on a noise corrupted resource management task

Mark J. F. Gales, Steve J. Young, S. Young, 1994, ICSLP.

Disfluency Detection for Spoken Learner English

Mark J. F. Gales, Kate Knill, Yu Wang, 2019, SLaTE.

CU-HTK April 2002 Switchboard System

Mark J. F. Gales, Thomas Hain, Gunnar Evermann, 2002 .

SLAM 2013 Speech, Language and Audio in Multimedia

Mark J. F. Gales, Yanhua Long, Thomas Hain, 2013 .

The application of parallel model combination to a large vocabulary dictation task

Mark J. F. Gales, Steve J. Young, S. Young, 1995, EUROSPEECH.

PMC for speech recognition in additive and convolutional noise

Mark J. F. Gales, Steve Young, Mark J. F. Gales, 1993 .

Augmented Statistical Models: Using Dynamic Kernels for Acoustic Models

Mark J. F. Gales, M. Gales, 2009 .

A speech processing system

Mark J. F. Gales, Kate Knill, Langzhou Chen, 2012 .

An adaptive speech recognition system and method using a cascade of transforms

Mark J. F. Gales, Kate Knill, K. K. Chin, 2010 .

Model-Based Approaches to Handling Uncertainty

Mark J. F. Gales, M. Gales, 2011, Robust Speech Recognition of Uncertain or Missing Data.

Adaptive Training and Noise Estimation for Model-Based Noise Compensation for ASR

M. Gales, F. Flego, 2012 .

Recent developments at Cambridge in broadcast news transcription

Mark J. F. Gales, Khe Chai Sim, Gunnar Evermann, 2004 .

Residue-Based Natural Language Adversarial Attack Detection

M. Gales, Vyas Raina, 2022, North American Chapter of the Association for Computational Linguistics.

Shifts 2.0: Extending The Dataset of Real Distributional Shifts

M. Gales, C. Granziera, K. Kyriakopoulos, 2022, ArXiv.

Multiple-Choice Question Generation: Towards an Automated Assessment Framework

M. Gales, Vatsal Raina, 2022, ArXiv.

Surprise Languages : Rapid-Response Cross-Language

M. Gales, Kenneth Heafield, A. Ragni, 2019 .

Edinburgh Research Explorer Multiple-average-voice-based speech synthesis

M. Gales, J. Yamagishi, P. Lanchantin, 2017 .

Residue-Based Natural Language Adversarial Attack Detection

M. Gales, Vyas Raina, 2022, NAACL.

Development of the 2004 CU-HTK English CTS systems using more than two thousand hours of data

Xunying Liu, Khe Chai Sim, Gunnar Evermann, 2004 .

Gender Bias and Universal Substitution Adversarial Attacks on Grammatical Error Correction Systems for Automated Assessment

M. Gales, Vyas Raina, 2022, ArXiv.

On Assessing and Developing Spoken ’Grammatical Error Correction’ Systems

M. Gales, Yiting Lu, Stefano Bannò, 2022, BEA.

Grammatical Error Correction Systems for Automated Assessment: Are They Susceptible to Universal Adversarial Attacks?

M. Gales, Yiting Lu, Vyas Raina, 2022, AACL.

Novel Structural-Scale Uncertainty Measures and Error Retention Curves: Application to Multiple Sclerosis

M. Gales, C. Granziera, A. Malinin, 2022, 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI).

L2 proficiency assessment using self-supervised speech representations

M. Gales, K. Knill, Vyas Raina, 2022, ArXiv.

“World Knowledge” in Multiple Choice Reading Comprehension

M. Gales, Vatsal Raina, Adian Liusie, 2022, FEVER.

Precision matrix modelling for large vocabulary continuous speech recognition

Khe Chai Sim, Mark J. F. Gales, M. Gales, 2004 .

IBM's 10xReal-time broadcast news transciption used in the 1999 hub4 evaluation

Peder A. Olsen, Miroslav Novak, Lidia Mangu, 2000 .

Podcast Summary Assessment: A Resource for Evaluating Summary Assessment Methods

M. Gales, Potsawee Manakul, 2022, ArXiv.

1 Statistical Sequence Modelling

M. Gales, 2017 .

Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters

Heiga Zen, Mark J. F. Gales, Ranniery Maia, 2010, SSW.

Statistical parametric speech synthesis based on product of experts

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Discriminative Models for Speech Recognition

M.J.F. Gales, M. Gales, 2007, 2007 Information Theory and Applications Workshop.

Product of Gaussians for speech recognition

Mark J. F. Gales, S. S. Airey, M. Gales, 2006, Comput. Speech Lang..

Temporally varying model parameters for large vocabulary continuous speech recognition

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2005, INTERSPEECH.

Basis superposition precision matrix modelling for large vocabulary continuous speech recognition

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Switching linear dynamical systems for speech recognition

Mark J. F. Gales, Av Rosti, M. Gales, 2003 .

Multi-Language Neural Network Language Models

Mark J. F. Gales, Kate Knill, Anton Ragni, 2016, INTERSPEECH.

Ensemble Distribution Distillation pdf

Andrey Malinin, Mark Gales, Bruno Mlodozeniec, 2019, ICLR.

Multi-task ensembles with teacher-student training

Mark J. F. Gales, Jeremy Heng Meng Wong, M. Gales, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Investigation of back-off based interpolation between recurrent neural network and n-gram language models

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Improving the training and evaluation efficiency of recurrent neural network language models

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Paraphrastic language models

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2014, Comput. Speech Lang..

Paraphrastic neural network language models

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Paraphrastic language models and combination with neural network language models

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Cross-domain paraphrasing for improving language modelling using out-of-domain data

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2013, INTERSPEECH.

Use of contexts in language model interpolation and adaptation

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2009, Comput. Speech Lang..

Context dependent language model adaptation

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2008, INTERSPEECH.

Automatic transcription of conversational telephone speech

Mark J. F. Gales, Lan Wang, Daniel Povey, 2005, IEEE Transactions on Speech and Audio Processing.

Automatic transcription of conversational telephone speech: development of the CU-HTK 2002 system

Daniel Povey, Thomas Hain, Xunying Liu, 2003 .

Augmented Statistical Models for Speech Recognition

Mark J. F. Gales, Martin I. Layton, M. Gales, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Training Augmented Models Using SVMs

Mark J. F. Gales, Martin I. Layton, M. Gales, 2006, IEICE Trans. Inf. Syst..

Maximum margin training of generative kernels

Mark J. F. Gales, M. I. Layton, M. Gales, 2004 .

Using SVMS and discriminative models for speech recognition

Mark J. F. Gales, N. D. Smith, M. Gales, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The efficient incorporation of MLP features into automatic speech recognition systems

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2011, Comput. Speech Lang..

Morphological decomposition in Arabic ASR systems

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2012, Comput. Speech Lang..

Infinite structured support vector machines for speech recognition

Mark J. F. Gales, Rogier C. van Dalen, Jingzhou Yang, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Structured Discriminative Models for Sequential Data Classification

Shi-Xiong Zhang, Mark Gales, M. Gales, 2010 .

Discriminative semi-parametric trajectory model for speech recognition

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2007, Comput. Speech Lang..

Factored Semi-Tied Covariance Matrices

Mark J. F. Gales, M. Gales, 2000, NIPS.

Cepstral parameter compensation for HMM recognition in noise

Mark J. F. Gales, Steve J. Young, S. Young, 1993, Speech Commun..

Robust speech recognition in additive and convolutional noise using parallel model combination

Mark J. F. Gales, Steve J. Young, S. Young, 1995, Comput. Speech Lang..

Improving reverberant VTS for hands-free robust speech recognition

Yongqiang Wang, Mark J. F. Gales, M. Gales, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Model-based approaches to handling additive noise in reverberant environments

Y.-Q. Wang, M. J. F. Gales, M. Gales, 2011, 2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays.

Robust continuous speech recognition using parallel model combination

Mark J. F. Gales, Steve J. Young, S. Young, 1996, IEEE Trans. Speech Audio Process..

Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness

Andrey Malinin, Mark Gales, M. Gales, 2019, NeurIPS.

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

M. Gales, Potsawee Manakul, Adian Liusie, 2023, arXiv.org.

MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization

M. Gales, Potsawee Manakul, Adian Liusie, 2023, ArXiv.

Stimulated training for automatic speech recognition and keyword search in limited resource conditions

Mark J. F. Gales, Kate Knill, Anton Ragni, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks

Y. Gal, M. Gales, A. Malinin, 2021, NeurIPS Datasets and Benchmarks.

Structured Support Vector Machines for Noise Robust Continuous Speech Recognition

Mark J. F. Gales, Shi-Xiong Zhang, M. Gales, 2011, INTERSPEECH.

Structured Log Linear Models for Noise Robust Speech Recognition

Mark J. F. Gales, Anton Ragni, Shi-Xiong Zhang, 2010, IEEE Signal Processing Letters.

Uncertainty Estimation in Autoregressive Structured Prediction

Mark J. F. Gales, Andrey Malinin, M. Gales, 2021, ICLR.

Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets pdf

Andrey Malinin, Mark Gales, Max Ryabinin, 2021, NeurIPS.

Minimum phone error training of precision matrix models

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

Minimum Phone Error Training of

Mark J. F. Gales, Khe Chai Sim, M. Gales, 2006 .

Who Needs Decoders? Efficient Estimation of Sequence-level Attributes

M. Gales, Adian Liusie, Puria Radmard, 2023, ArXiv.

Annotating large lattices with the exact word error

Mark J. F. Gales, Rogier C. van Dalen, M. Gales, 2015, INTERSPEECH.

Cluster adaptive training of average voice models

Mark J. F. Gales, Yannis Stylianou, Vincent Wan, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Building HMM-TTS Voices on Diverse Data

Mark J. F. Gales, Masami Akamine, Norbert Braunschweiler, 2014, IEEE Journal of Selected Topics in Signal Processing.

Speech intonation for TTS: study on evaluation methodology

Mark J. F. Gales, Vincent Wan, BalaKrishna Kolluru, 2014, INTERSPEECH.

Noise-robust TTS speaker adaptation with statistics smoothing

Mark J. F. Gales, Kayoko Yanagisawa, Langzhou Chen, 2014, INTERSPEECH.

Noise robustness in HMM-TTS speaker adaptation

Simon King, Mark J. F. Gales, Vincent Wan, 2013, SSW.

Combining multiple high quality corpora for improving HMM-TTS

Heiga Zen, Mark J. F. Gales, Kate Knill, 2012, INTERSPEECH.

Unsupervised clustering of emotion and voice styles for expressive TTS

Mark J. F. Gales, Kate Knill, Florian Eyben, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Exploring Rich Expressive Information from Audiobook Data Using Cluster Adaptive Training

Mark J. F. Gales, Masami Akamine, Vincent Wan, 2012, INTERSPEECH.

Speech factorization for HMM-TTS based on cluster adaptive training

Mark J. F. Gales, Kate Knill, Masami Akamine, 2012, INTERSPEECH.

Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?

Yamato Ohtani, Mark J. F. Gales, Kate Knill, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Decision tree-based context clustering based on cross validation and hierarchical priors

Heiga Zen, Mark J. F. Gales, H. Zen, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech recognition and keyword spotting for low-resource languages: Babel project research at CUED

Mark J. F. Gales, Kate Knill, Anton Ragni, 2014, SLTU.

Efficient Use of End-to-End Data in Spoken Language Processing

Mark J. F. Gales, Yu Wang, Yiting Lu, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Student-Teacher Training with Diverse Decision Tree Ensembles

Mark J. F. Gales, Jeremy Heng Meng Wong, M. Gales, 2017, INTERSPEECH.

Incorporating Uncertainty into Deep Learning for Spoken Language Assessment

Mark J. F. Gales, Kate Knill, Andrey Malinin, 2017, ACL.

Data augmentation for low resource languages

Mark J. F. Gales, Kate Knill, Anton Ragni, 2014, INTERSPEECH.

Spoken Language 'Grammatical Error Correction'

Mark J. F. Gales, Yu Wang, Yiting Lu, 2020, INTERSPEECH.

Directed decision trees for generating complementary systems

Mark J. F. Gales, Catherine Breslin, M. Gales, 2009, Speech Commun..

Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks

Mark J. F. Gales, Anton Ragni, Qiujia Li, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models

Mark J. F. Gales, Philip C. Woodland, Panagiota Karanasou, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Cambridge university transcription systems for the multi-genre broadcast challenge

Mark J. F. Gales, Chao Zhang, Linlin Wang, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

M. Gales, Potsawee Manakul, Adian Liusie, 2023, ArXiv.

Multilingual representations for low resource speech recognition and keyword search

Brian Kingsbury, Bhuvana Ramabhadran, Michael Picheny, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Automatic Detection of Accent and Lexical Pronunciation Errors in Spontaneous Non-Native English Speech

Mark J. F. Gales, Kate Knill, Konstantinos Kyriakopoulos, 2020, INTERSPEECH.

Automatic Grammatical Error Detection of Non-native Spoken Learner English

Mark J. F. Gales, Kate Knill, Potsawee Manakul, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improved neural network based language modelling and adaptation

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2010, INTERSPEECH.

CUED_SPEECH at TREC 2020 Podcast Summarisation Track

M. Gales, Potsawee Manakul, 2020, TREC.

Exploiting Future Word Contexts in Neural Network Language Models for Speech Recognition

Mark J. F. Gales, Yu Wang, Anton Ragni, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Speaker diarisation and longitudinal linking in multi-genre broadcast data

Mark J. F. Gales, Chao Zhang, Linlin Wang, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Structured Discriminative Models For Speech Recognition: An Overview

Mark Gales, S. Watanabe, E. Fosler-Lussier, 2012, IEEE Signal Processing Magazine.

Structured discriminative models for speech recognition

Mark J. F. Gales, Rogier C. van Dalen, Anton Ragni, 2012, MLSLP.

SVMS, SCORE-SPACES AND MAXIMUM MARGIN STATISTICAL MODELS

Mark J. F. Gales, Martin Layton, M. Gales, 2004 .

Rao-Blackwellised Gibbs sampling for switching linear dynamical systems

Mark J. F. Gales, Antti-Veikko I. Rosti, M. Gales, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Generalised linear Gaussian models

Mark J. F. Gales, Av Rosti, M. Gales, 2001 .

Paraphrastic recurrent neural network language models

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Identifying Adversarially Attackable and Robust Samples

M. Gales, Vyas Raina, 2023, ArXiv.

Complementary Systems for Off-Topic Spoken Response Detection

Kate Knill, Vatsal Raina, Mark Gales, 2020, BEA.

Long-Span Summarization via Local Attention and Content Selection

Mark J. F. Gales, Potsawee Manakul, M. Gales, 2021, ACL.

Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems

Mark J. F. Gales, Potsawee Manakul, M. Gales, 2021, EMNLP.

Zero-shot NLG evaluation through Pairware Comparisons with LLMs

M. Gales, Potsawee Manakul, Adian Liusie, 2023, ArXiv.

The MGB challenge: Evaluating multi-genre broadcast media recognition

Mark J. F. Gales, Oscar Saz-Torralba, Thomas Hain, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Should Ensemble Members Be Calibrated? pdf

Xixin Wu, Mark Gales, M. Gales, 2021, ArXiv.

An initial investigation of long-term adaptation for meeting transcription

Mark J. F. Gales, Kate Knill, K. K. Chin, 2014, INTERSPEECH.

Environmentally robust ASR front-end for deep neural network acoustic models

T. Yoshioka, M.J.F. Gales, M. Gales, 2015, Comput. Speech Lang..

State-based Gaussian selection in large vocabulary continuous speech recognition using HMMs

Mark J. F. Gales, Kate Knill, Steve J. Young, 1999, IEEE Trans. Speech Audio Process..

Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems

Mark J. F. Gales, C. Zhang, L. Wang, 2016, INTERSPEECH.

Regression Prior Networks pdf

Mark Gales, Andrey Malinin, Ivan Provilkov, 2020, ArXiv.

Parallel Attention Forcing for Machine Translation

M. Gales, Qingyun Dou, 2022, ArXiv.

Attention Forcing for Machine Translation pdf

Mark J. F. Gales, Potsawee Manakul, Yiting Lu, 2021, ArXiv.

Ensemble Distillation Approaches for Grammatical Error Correction pdf

Yassir Fathullah, Mark Gales, Andrey Malinin, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Attention Forcing for Sequence-to-sequence Model Training pdf

Mark J. F. Gales, Qingyun Dou, Yiting Lu, 2019, ArXiv.

Disfluency Detection for Spoken Learner English

Mark J. F. Gales, Kate Knill, Yu Wang, 2019, SLaTE.

Stimulated Deep Neural Network for Speech Recognition

Mark J. F. Gales, Khe Chai Sim, Panagiota Karanasou, 2016, INTERSPEECH.

Improving the interpretability of deep neural networks with stimulated learning

Mark J. F. Gales, Khe Chai Sim, Shawn Tan, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Investigation of multilingual deep neural networks for spoken term detection

Mark J. F. Gales, Kate Knill, Chao Zhang, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Hierarchical RNNs for Waveform-Level Speech Synthesis

Mark J. F. Gales, Zhiyi Ma, Gilles Degottex, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Deliberation Networks and How to Train Them

M. Gales, Qingyun Dou, 2022, ArXiv.

Attention Forcing for Speech Synthesis

Mark J. F. Gales, Joshua Efiong, Qingyun Dou, 2020, INTERSPEECH.

Abstractive Spoken Document Summarization Using Hierarchical Model with Multi-Stage Attention Diversity Optimization

Mark J. F. Gales, Potsawee Manakul, Linlin Wang, 2020, INTERSPEECH.

Generating multiple-accent pronunciations for TTS using joint sequence model interpolation

Mark J. F. Gales, Vincent Wan, BalaKrishna Kolluru, 2014, INTERSPEECH.

Gaussian Process Experts for Voice Conversion

Heiga Zen, Mark J. F. Gales, Nicholas Pilkington, 2011, INTERSPEECH.

Adapting an ASR Foundation Model for Spoken Language Assessment

M. Gales, K. Knill, Mengjie Qian, 2023, ArXiv.

Self-Distribution Distillation: Efficient Uncertainty Estimation

M. Gales, Yassir Fathullah, 2022, UAI.

Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks

Anton Ragni, Mark Gales, Alexandros Kastanos, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation

Mark J. F. Gales, Anton Ragni, Qiujia Li, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automatic Speech Recognition System Development in the "Wild"

Mark J. F. Gales, Anton Ragni, M. Gales, 2018, INTERSPEECH.

Structured SVMs for Automatic Speech Recognition

Mark J. F. Gales, Shi-Xiong Zhang, M. Gales, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Towards Using Conversations with Spoken Dialogue Systems in the Automated Assessment of Non-Native Speakers of English

Mark J. F. Gales, Kate Knill, Rogier C. van Dalen, 2016, SIGDIAL Conference.

A fast and flexible implementation of parallel model combination

Mark J. F. Gales, Steve J. Young, S. Young, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Discriminative language model adaptation for Mandarin broadcast speech transcription and translation

William J. Byrne, Mark J. F. Gales, Marcus Tomalin, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Speech Recognition System Combination for Machine Translation

Mark J. F. Gales, Spyridon Matsoukas, Jean-Luc Gauvain, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Improving Speech Transcription for Mandarin-English Translation

Mark J. F. Gales, Marcus Tomalin, Lan Wang, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Consensus Network Decoding for Statistical Machine Translation System Combination

Hichem Sahbi, William J. Byrne, Mark J. F. Gales, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Long-Span Dependencies in Transformer-based Summarization Systems pdf

Mark J. F. Gales, Potsawee Manakul, M. Gales, 2021, ArXiv.

Low-Resource Speech Recognition and Keyword-Spotting

Mark J. F. Gales, Kate Knill, Anton Ragni, 2017, SPECOM.

The development of the cambridge university alignment systems for the multi-genre broadcast challenge

Mark J. F. Gales, Chao Zhang, Linlin Wang, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Ensemble Approaches for Uncertainty in Spoken Language Assessment

Mark J. F. Gales, Kate Knill, Xixin Wu, 2020, INTERSPEECH.

Training and adapting MLP features for Arabic speech recognition

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Complementary System Generation using Directed Decision Trees

Mark J. F. Gales, Catherine Breslin, M. Gales, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

A Deep Learning Approach to Automatic Characterisation of Rhythm in Non-Native English Speech

Mark J. F. Gales, Konstantinos Kyriakopoulos, Kate M. Knill, 2019, INTERSPEECH.

Sample Attackability in Natural Language Adversarial Attacks

M. Gales, Vyas Raina, 2023, TRUSTNLP.

CUED at ProbSum 2023: Hierarchical Ensemble of Summarization Models

M. Gales, Vatsal Raina, Vyas Raina, 2023, BIONLP.

Unsupervised training and directed manual transcription for LVCSR

Mark J. F. Gales, Lan Wang, Kai Yu, 2010, Speech Commun..

Unsupervised training with directed manual transcription for recognising Mandarin broadcast audio

Mark J. F. Gales, Kai Yu, Philip C. Woodland, 2007, INTERSPEECH.

Factor analysed hidden Markov models for speech recognition

Mark J. F. Gales, Antti-Veikko I. Rosti, M. Gales, 2004, Comput. Speech Lang..

Factor analysed hidden Markov models

Mark J. F. Gales, Antti-Veikko I. Rosti, M. Gales, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Noisy Constrained Maximum-Likelihood Linear Regression for Noise-Robust Speech Recognition

Mark J. F. Gales, D. K. Kim, M. Gales, 2011, IEEE Transactions on Audio, Speech, and Language Processing.

Asymptotically exact noise-corrupted speech likelihoods

Mark J. F. Gales, Rogier C. van Dalen, M. Gales, 2010, INTERSPEECH.

Improving joint uncertainty decoding performance by predictive methods for noise robust speech recognition

Mark J. F. Gales, K. K. Chin, Haitian Xu, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

Predictive linear transforms for noise robust speech recognition

Mark J. F. Gales, Rogier C. van Dalen, M. Gales, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Joint uncertainty decoding for noise robust speech recognition

Mark J. F. Gales, Hank Liao, M. Gales, 2005, INTERSPEECH.

Can Generative Large Language Models Perform ASR Error Correction?

M. Gales, K. Knill, Mengjie Qian, 2023, ArXiv.

MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization

M. Gales, Potsawee Manakul, Adian Liusie, 2023, ArXiv.

Log-Linear System Combination Using Structured Support Vector Machines

Mark J. F. Gales, Kate Knill, Jingzhou Yang, 2016, INTERSPEECH.

Structured discriminative models for noise robust continuous speech recognition

Mark J. F. Gales, Anton Ragni, M. Gales, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Discriminative adaptation for speaker verification

Mark J. F. Gales, Chris Longworth, M. Gales, 2006, INTERSPEECH.

Acoustic Modelling Using Continuous Rational Kernels

Mark J. F. Gales, Martin I. Layton, M. Gales, 2005, 2005 IEEE Workshop on Machine Learning for Signal Processing.

Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties

M. Gales, Guoxuan Xia, Yassir Fathullah, 2023, UAI.

The Cambridge University March 2005 speaker diarisation system

Mark J. F. Gales, Philip C. Woodland, Rohit Sinha, 2005, INTERSPEECH.

Universal Adversarial Attacks on Spoken Language Assessment Systems

Mark J. F. Gales, Kate Knill, Vyas Raina, 2020, INTERSPEECH.

Multimodal Fusion

Hank Liao, Mark Gales, M. Gales, 2009, Encyclopedia of Biometrics.

Improving Interpretability and Regularization in Deep Learning

Mark J. F. Gales, Anton Ragni, Khe Chai Sim, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models

M. Gales, Potsawee Manakul, Adian Liusie, 2023, 2307.07889.

N-best T5: Robust ASR Error Correction using Multiple Input Hypotheses and Constrained Decoding Space

M. Gales, K. Knill, Mengjie Qian, 2023, INTERSPEECH 2023.

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

M. Gales, Potsawee Manakul, Adian Liusie, 2023, EMNLP.

Investigation of acoustic units for LVCSR systems

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Off-topic Response Detection for Spontaneous Spoken English Assessment

Yu Wang, Mark J. F. Gales, Kate Knill, 2016, ACL.

Towards End-to-End Spoken Grammatical Error Correction

M. Gales, K. Knill, Stefano Bannò, 2023, ArXiv.

Annotation of L2 English Speech for Developing and Evaluating End-to-End Spoken Grammatical Error Correction

M. Gales, K. Knill, D. Nicholls, 2023, 9th Workshop on Speech and Language Technology in Education (SLaTE).

System combination and score normalization for spoken term detection

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Sequence Student-Teacher Training of Deep Neural Networks

Mark J. F. Gales, Jeremy Heng Meng Wong, M. Gales, 2016, INTERSPEECH.

Analysing Bias in Spoken Language Assessment Using Concept Activation Vectors

Mark J. F. Gales, Kate Knill, Xizi Wei, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Mitigating Word Bias in Zero-shot Prompt-based Classifiers

M. Gales, Potsawee Manakul, Adian Liusie, 2023, IJCNLP.

Infinite support vector machines in speech recognition

Mark J. F. Gales, Rogier C. van Dalen, Jingzhou Yang, 2013, INTERSPEECH.

Generative Kernels and Score-Spaces for Classi cation of Speech : Progress Report iii

M. Gales, R. V. Dalen, J. Yang, 2012 .

Importance sampling to compute likelihoods of noise-corrupted speech

Mark J. F. Gales, Rogier C. van Dalen, M. Gales, 2013, Comput. Speech Lang..

A theoretical bound for noise-robust speech recognition

M. Gales, R. V. Dalen, R. C. Van Dalen, 2010 .

A Deep Learning Approach to Assessing Non-native Pronunciation of English Using Phone Distances

Mark J. F. Gales, Kate Knill, Konstantinos Kyriakopoulos, 2018, INTERSPEECH.

Active Memory Networks for Language Modeling

Mark J. F. Gales, Anton Ragni, Xie Chen, 2018, INTERSPEECH.

An attention based model for off-topic spontaneous spoken response detection: An Initial Study

Yu Wang, Mark J. F. Gales, Kate Knill, 2017, SLaTE.

Sequence Teacher-Student Training of Acoustic Models for Automatic Free Speaking Language Assessment

Mark J. F. Gales, Kate Knill, Anton Ragni, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

An analysis of student-teacher information propagation

M. Gales, J. H. M. Wong, 2017 .

Handbook of Natural Language Processing and Machine Translation

Kai Yu, Mark J. F. Gales, Philip C. Woodland, 2012 .

Investigating Bidirectional Recurrent Neural Network Language Models for Speech Recognition

Mark J. F. Gales, Anton Ragni, X. Chen, 2017, INTERSPEECH.

Recurrent neural network language model adaptation for multi-genre broadcast speech recognition

Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, 2015, INTERSPEECH.

General Sequence Teacher–Student Learning

Yu Wang, Mark John Francis Gales, Jeremy Heng Meng Wong, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation

Mark J. F. Gales, C. Zhang, Linlin Wang, 2015, INTERSPEECH.

Unsupervised Training for Mandarin Broadcast News and Conversation Transcription

Mark J. F. Gales, Lan Wang, Philip C. Woodland, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Development of the CUHTK 2004 Mandarin conversational telephone speech transcription system

Mark J. F. Gales, Xunying Liu, Khe Chai Sim, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Discriminative map for acoustic model adaptation

Mark J. F. Gales, Daniel Povey, Philip C. Woodland, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Prior Networks for Detection of Adversarial Attacks pdf

Mark J. F. Gales, Andrey Malinin, M. Gales, 2018, ArXiv.

Efficient Sample-Specific Encoder Perturbations

M. Gales, Yassir Fathullah, 2024, NAACL.