Philip C. Woodland

发表

Posterior probability decoding, confidence estimation and system combination

Gunnar Evermann, Philip C. Woodland, P. Woodland, 2000 .

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).

The 1998 HTK broadcast news transcription system: development and results

Thomas Hain, Philip C. Woodland, Daniel Povey, 1999 .

Spontaneous speech recognition for the credit card corpus using the HTK toolkit

Philip C. Woodland, Steve Young, William Byrne, 1994, IEEE Trans. Speech Audio Process..

Using VTLN for broadcast news transcription

Mark J. F. Gales, Thomas Hain, Philip C. Woodland, 2004, INTERSPEECH.

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).

The 1997 HTK broadcast news transcription system

Thomas Hain, Philip C. Woodland, Thomas Niesler, 1998 .

Frame discrimination training for HMMs for large vocabulary speech recognition

Daniel Povey, Philip C. Woodland, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

State clustering in hidden Markov model-based continuous speech recognition

Steve J. Young, Philip C. Woodland, S. Young, 1994, Comput. Speech Lang..

Spoken language systems technology workshop

Steve Young, Philip C. Woodland, C. J. Leggetter, 1995 .

Unsupervised discriminative adaptation using discriminative mapping transforms

Mark J. F. Gales, Kai Yu, Philip C. Woodland, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Graphone Model Interpolation and Arabic Pronunciation Generation

Mark J. F. Gales, Philip C. Woodland, T. Li, 2011, INTERSPEECH.

Recent advances in broadcast news transcription

Thomas Hain, Gunnar Evermann, Philip C. Woodland, 2003 .

High Order Recurrent Neural Networks for Acoustic Modelling

Philip C. Woodland, Chao Zhang, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Use of contexts in language model interpolation and adaptation

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

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.

Corrections to "Automatic Transcription of Conversational Telephone Speech"

Mark J. F. Gales, Lan Wang, Daniel Povey, 2006, IEEE Trans. Speech Audio Process..

DNN speaker adaptation using parameterised sigmoid and ReLU hidden activation functions

C. Zhang, Philip C. Woodland, P. Woodland, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Experiments in broadcast news transcription

Thomas Niesler, Thomas Hain, Steve J. Young, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

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.

The HTK tied-state continuous speech recogniser

Steve J. Young, Philip C. Woodland, S. Young, 1993, EUROSPEECH.

Using relative duration in large vocabulary speech recognition

Philip C. Woodland, M. Jones, 1993, EUROSPEECH.

Handbook of Natural Language Processing and Machine Translation

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

New features in the CU-HTK system for transcription of conversational telephone speech

Daniel Povey, Thomas Hain, Gunnar Evermann, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Large scale discriminative training for speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2000 .

MMI-MAP and MPE-MAP for acoustic model adaptation

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

Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition

Philip C. Woodland, Chao Zhang, Qiujia Li, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

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.

Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems

Yu Wang, Mark J. F. Gales, Chao Zhang, 2018, INTERSPEECH.

The efficient incorporation of MLP features into automatic speech recognition systems

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

Improving retrieval on imperfect speech transcriptions (poster abstract)

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 1999, SIGIR '99.

Emotion recognition by fusing time synchronous and time asynchronous representations pdf

Chao Zhang, Philip C. Woodland, Wen Wu, 2020, ArXiv.

Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems

Mark J. F. Gales, Marcus Tomalin, Xunying Liu, 2011, INTERSPEECH.

An investigation into vocal tract length normalisation

Philip C. Woodland, Luís Felipe Uebel, L. F. Uebel, 1999, EUROSPEECH.

Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch

Yongqiang Wang, Mark J. F. Gales, Xunying Liu, 2014, INTERSPEECH.

Unsupervised Adaptation With Discriminative Mapping Transforms

Mark J. F. Gales, Kai Yu, Philip C. Woodland, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

The use of accent-specific pronunciation dictionaries in acoustic model training

Philip C. Woodland, Jason J. Humphries, P. Woodland, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Language model combination and adaptation usingweighted finite state transducers

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Speaker clustering using direct maximisation of the MLLR-adapted likelihood

Philip C. Woodland, Sue E. Johnson, 1998, ICSLP.

Using accent-specific pronunciation modelling for robust speech recognition

Philip C. Woodland, David J. B. Pearce, Jason J. Humphries, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

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).

Phonetic pronunciations for arabic speech-to-text systems

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Standalone training of context-dependent deep neural network acoustic models

Philip C. Woodland, Chao Zhang, P. Woodland, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Variable-length categoryn-gram language models

Thomas Niesler, Philip C. Woodland, 1999, Comput. Speech Lang..

Application of an auditory model to the computer simulation of hearing impairment: preliminary results

Philip C. Woodland, C. Giguere, A. J. Robinson, 1993 .

Generating and evaluating segmentations for automatic speech recognition of conversational telephone speech

Kai Yu, Gunnar Evermann, Philip C. Woodland, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Discriminative optimisation of large vocabulary recognition systems

Steve J. Young, Philip C. Woodland, V. Valtchev, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

The Cambridge University Multimedia Document Retrieval demo system (demonstration session)

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 2000, SIGIR '00.

Optimising hidden Markov models using discriminative output distributions

Philip C. Woodland, D. R. Cole, 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

The development of the 1994 HTK large vocabulary speech recognition system

Philip C. Woodland, C. J. Leggetter, P. Woodland, 1995 .

Spoken document representations for probabilistic retrieval

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 2000, Speech Commun..

MMIE training of large vocabulary recognition systems

Steve J. Young, Philip C. Woodland, V. Valtchev, 1997, Speech Communication.

The Cambridge University spoken document retrieval system

Karen Spärck Jones, Philip C. Woodland, Gareth L. Moore, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Automatic complexity control for HLDA systems

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

Improved DNN-based segmentation for multi-genre broadcast audio

Mark J. F. Gales, Chao Zhang, Linlin Wang, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition pdf

Liangliang Cao, Philip C. Woodland, Yu Zhang, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker adaptation using lattice-based MLLR

Philip C. Woodland, Lf Uebel, 2001 .

Improving broadcast news transcription by lightly supervised discriminative training

Ricky Ho Yin Chan, Philip C. Woodland, P. Woodland, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The development of the HTK Broadcast News transcription system: An overview

Philip C. Woodland, P. Woodland, 2002, Speech Commun..

CUED-RNNLM — An open-source toolkit for efficient training and evaluation of recurrent neural network language models

Mark J. F. Gales, X. Chen, Philip C. Woodland, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Using Sub-word-level Information for Confidence Estimation with Conditional Random Field Models

Philip C. Woodland, Matthew Stephen Seigel, 2012, INTERSPEECH.

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.

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).

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

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

Automatic transcription of conversational telephone speech

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

Adaptation of deep neural network acoustic models using factorised i-vectors

Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland, 2014, INTERSPEECH.

Formant tracking using continuous density hidden markov models

Philip C. Woodland, 1986 .

PyHTK: Python Library and ASR Pipelines for HTK

Philip C. Woodland, Chao Zhang, Florian Kreyssig, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker adaptation of continuous density HMMs using multivariate linear regression

Philip C. Woodland, Chris Leggetter, P. Woodland, 1994, ICSLP.

I-vector estimation using informative priors for adaptation of deep neural networks

Mark J. F. Gales, Philip C. Woodland, Panagiota Karanasou, 2015, INTERSPEECH.

Unsupervised training and directed manual transcription for LVCSR

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

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.

Recognition ********* a dynamic network decoder design for large vocabulary speech recognition

Steve J. Young, Philip C. Woodland, V. Valtchev, 1994, ICSLP.

Tree-based state clustering for large vocabulary speech recognition

Steve Young, Philip C. Woodland, Jj Odell, 1994, Proceedings of ICSIPNN '94. International Conference on Speech, Image Processing and Neural Networks.

Discriminative Neural Clustering for Speaker Diarisation pdf

Philip C. Woodland, Chao Zhang, Qiujia Li, 2019, ArXiv.

Exploiting variable-width features in large vocabulary speech recognition

Philip C. Woodland, M. Jones, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Flexible speaker adaptation for large vocabulary speech recognition

Philip C. Woodland, Chris Leggetter, 1995, EUROSPEECH.

Cluster identification for speaker-environment tracking

Philip C. Woodland, J. T. Wickramaratna, 2002, INTERSPEECH.

Maximum mutual information training of hidden Markov models with vector linear predictors

Philip C. Woodland, K. K. Chin, P. Woodland, 2002, INTERSPEECH.

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).

Development of the CU-HTK 2004 broadcast news transcription systems

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

Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages

Mark J. F. Gales, Kate Knill, Anton Ragni, 2015, INTERSPEECH.

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.

Transcription of multi-genre media archives using out-of-domain data

Mark J. F. Gales, Yanhua Long, Pierre Lanchantin, 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

MPE-based discriminative linear transforms for speaker adaptation

Lan Wang, Philip C. Woodland, 2008, Comput. Speech Lang..

Language modelling for Russian and English using words and classes

Philip C. Woodland, Edward W. D. Whittaker, 2003, Comput. Speech Lang..

Combining Information Sources for Confidence Estimation with CRF Models

Philip C. Woodland, Matthew Stephen Seigel, P. Woodland, 2011, INTERSPEECH.

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).

Automatic Transcription of Multi-genre Media Archives

Mark J. F. Gales, Yanhua Long, Oscar Saz-Torralba, 2013, SLAM@INTERSPEECH.

An experimental comparison of connectionist and conventional classification systems on natural data

Philip C. Woodland, S. G. Smyth, P. Woodland, 1990, Speech Commun..

Segment generation and clustering in the HTK broadcast news transcription system

Steve Young, Thomas Hain, Philip C. Woodland, 1998 .

Improvements in linear transform based speaker adaptation

Philip C. Woodland, Luís Felipe Uebel, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Recent improvements to the Cambridge Arabic Speech-to-Text systems

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Hidden Markov models using vector linear prediction and discriminative output distributions

Philip C. Woodland, P. Woodland, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Language model cross adaptation for LVCSR system combination

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2013, Comput. Speech Lang..

Development of a phonetic system for large vocabulary Arabic speech recognition

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

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.

Unsupervised training with directed manual transcription for recognising Mandarin broadcast audio

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

Rapid speaker adaptation using model prediction

Philip C. Woodland, S. M. Ahadi, P. Woodland, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

The Cambridge Multimedia Document Retrieval Project: summary of experiments

Philip C. Woodland, Karen Sparck Jones, S. E. Johnson, 2001 .

Large scale discriminative training of hidden Markov models for speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2002, Comput. Speech Lang..

Data underpinning "I-Vector Estimation Using Informative Priors for Adaptation of Deep Neural Networks"

Mark J. F. Gales, Philip C. Woodland, Penny Karanasou, 2015 .

A method for direct audio search with applications to indexing and retrieval

Philip C. Woodland, Sue E. Johnson, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

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).

Particle-based language modelling

Philip C. Woodland, Edward W. D. Whittaker, 2000, INTERSPEECH.

Paraphrastic language models

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

Semi-tied Units for Efficient Gating in LSTM and Highway Networks pdf

Chao Zhang, Philip C. Woodland, 2018, INTERSPEECH.

Speaker adaptation for continuous density HMMs: a review

Philip C. Woodland, 2001 .

A hidden Markov-model-based trainable speech synthesizer

Philip C. Woodland, Robert E. Donovan, P. Woodland, 1999, Comput. Speech Lang..

A composite model of the auditory periphery with feedback regulation

Philip C. Woodland, Christian Giguère, 1992 .

A general artificial neural network extension for HTK

Chao Zhang, Philip C. Woodland, P. Woodland, 2015, INTERSPEECH.

Improvements in an HMM-based speech synthesiser

Philip C. Woodland, Robert E. Donovan, P. Woodland, 1995, EUROSPEECH.

The 1998 HTK system for transcription of conversational telephone speech

Thomas Niesler, Thomas Hain, Philip C. Woodland, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Dynamic HMM selection for continuous speech recognition

Thomas Hain, Philip C. Woodland, 1999, EUROSPEECH.

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).

Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings

Philip C. Woodland, Florian L. Kreyssig, 2020, INTERSPEECH.

Speech analysis using a nonlinear cochlear model with feedback regulation

Philip C. Woodland, Christian Giguère, 1992 .

HTK V1.5: User, Reference and Programmer Manuals

Steve Young, Philip C. Woodland, William Byrne, 1993 .

Hidden Markov models using shared vector linear predictors

Philip C. Woodland, B. A. Maxwell, P. Woodland, 1993, EUROSPEECH.

The HTK large vocabulary recognition system for the 1995 ARPA H3 task

Philip C. Woodland, Valtchev, Mjf Gales, 1996 .

Automatic capitalisation generation for speech input

Ji-Hwan Kim, Philip C. Woodland, P. Woodland, 2004, Comput. Speech Lang..

An investigation into the the interactions between speaker diarisation systems and automatic speech transcription

Gunnar Evermann, Philip C. Woodland, Do Yeong Kim, 2003 .

MPE-based discriminative linear transform for speaker adaptation

Lan Wang, Philip C. Woodland, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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).

Automatic speech synthesiser parameter estimation using HMMs

Philip C. Woodland, Robert E. Donovan, P. Woodland, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Improving lightly supervised training for broadcast transcription

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

A PLSA-based language model for conversational telephone speech

Philip C. Woodland, David Mrva, P. Woodland, 2004, INTERSPEECH.

WSJCAM0 corpus and recording description

Steve Young, Philip C. Woodland, D. Pye, 1994 .

Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2011, INTERSPEECH.

Audio Indexing and Retrieval of Complete Broadcoast News Shows

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 2000, RIAO.

Large vocabulary continuous speech recognition using HTK

Steve J. Young, Philip C. Woodland, V. Valtchev, 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

Improving environmental robustness in large vocabulary speech recognition

Mark J. F. Gales, Philip C. Woodland, David Pye, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

General query expansion techniques for spoken document retrieval

K. Sparck Jones, Philip C. Woodland, S. E. Johnson, 1999 .

Relating dynamic brain states to dynamic machine states: human and machine solutions to the speech recognition problem

Li Su, Andrew Thwaites, William D. Marslen-Wilson, 2017 .

Direct sub-word confidence estimation with hidden-state conditional random fields

Philip C. Woodland, Matthew Stephen Seigel, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Mean and variance adaptation within the MLLR framework

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

Exploiting Chinese character models to improve speech recognition performance

Mark J. F. Gales, Xunying Liu, Philip C. Woodland, 2009, INTERSPEECH.

Efficient class-based language modelling for very large vocabularies

Philip C. Woodland, Edward W. D. Whittaker, P. Woodland, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

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.

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

Daniel Povey, Thomas Hain, Xunying Liu, 2003 .

A rule-based named entity recognition system for speech input

Ji-Hwan Kim, Philip C. Woodland, P. Woodland, 2000, INTERSPEECH.

Context dependent language model adaptation

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

Very deep convolutional neural networks for robust speech recognition

Philip C. Woodland, Yanmin Qian, P. Woodland, 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

Isolated word speech recognition based on connectionist techniques

Philip C. Woodland, 1990 .

Cambridge University Engineering Department

Philip C. Woodland, C. J. Leggetter, 1994 .

Data Underpinning "Joint Optimisation of Tandem Systems Using Gaussian Mixture Density Neural Network Discriminative Sequence Training"

Chao Zhang, Philip C. Woodland, 2017 .

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.

Unsupervised language model adaptation for Mandarin broadcast conversation transcription

Philip C. Woodland, David Mrva, P. Woodland, 2006, INTERSPEECH.

The use of state tying in continuous speech recognition

Steve J. Young, Philip C. Woodland, S. Young, 1993, EUROSPEECH.

Improved cross-task recognition using MMIE training

Mark J. F. Gales, Philip C. Woodland, R. Cordoba, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

The development of the Cambridge University RT-04 diarisation system

Srinivasan Umesh, Philip C. Woodland, S. E. Tranter, 2004 .

PARAPHRASTIC RECURRENT NEURAL NETWORK LANGUAGE

Xunying Liu, Philip C. Woodland, Xie Chen, 2015 .

Discriminative adaptive training using the MPE criterion

Philip C. Woodland, L. Wang, 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

Sequence training of DNN acoustic models with natural gradient

Adnan Haider, Philip C. Woodland, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Tree-Based State Tying for High Accuracy Modelling

Steve J. Young, Philip C. Woodland, J. J. Odell, 1994, HLT.

Structural metadata research in the EARS program

Andreas Stolcke, Mary P. Harper, Mari Ostendorf, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation

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

Large scale MMIE training for conversational telephone speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2000 .

Comparison of part-of-speech and automatically derived category-based language models for speech recognition

Thomas Niesler, Philip C. Woodland, Edward W. D. Whittaker, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Combining Natural Gradient with Hessian Free Methods for Sequence Training

Adnan Haider, Philip C. Woodland, P. Woodland, 2018, INTERSPEECH.

Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS

C. Zhang, Philip C. Woodland, Florian L. Kreyssig, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models

Philip C. Woodland, Chris Leggetter, P. Woodland, 1995, Comput. Speech Lang..

Improved discriminative training techniques for large vocabulary continuous speech recognition

Daniel Povey, Philip C. Woodland, P. Woodland, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

Training LVCSR systems on thousands of hours of data

Mark J. F. Gales, Kai Yu, Ricky Ho Yin Chan, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

The development of the 1996 HTK broadcast news transcription system

Steve Young, Philip C. Woodland, D. Pye, 1996 .

System combination with log-linear models

Mark J. F. Gales, Anton Ragni, C. Zhang, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Implementation of automatic capitalisation generation systems for speech input

Ji-Hwan Kim, Philip C. Woodland, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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

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

Modelling word-pair relations in a category-based language model

Thomas Niesler, Philip C. Woodland, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Speaker adaptation of HMMs using linear regression

Philip C. Woodland, C. J. Leggetter, P. Woodland, 1994 .

Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training

Philip C. Woodland, Chao Zhang, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Minimum Phone Error and I-smoothing for improved discriminative training

Daniel Povey, Philip C. Woodland, P. Woodland, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Improved Large-Margin Softmax Loss for Speaker Diarisation

Chao Zhang, Philip C. Woodland, Yassir Fathullah, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker adaptation: techniques and challenges

Philip C. Woodland, P. Woodland, 1999 .

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.

A combined punctuation generation and speech recognition system and its performance enhancement using prosody

Ji-Hwan Kim, Philip C. Woodland, P. Woodland, 2003, Speech Commun..

Combination of word-based and category-based language models

Thomas Niesler, Philip C. Woodland, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

Large vocabulary multilingual speech recognition using HTK

Steve J. Young, Philip C. Woodland, David Pye, 1995, EUROSPEECH.

Erratum: Language modelling for Russian and English using words and classes [Computer Speech and Language 17 (2003) 87-104]

Philip C. Woodland, Edward W. D. Whittaker, 2003, Comput. Speech Lang..

Improving retrieval on imperfect speech transcriptions

Philip C. Woodland, S. E. Johnson, P. Jourlin, 1999 .

A neural network speech recogniser for directory access applications

Philip C. Woodland, S. G. Smyth, 1990 .

Multi-level representations in speech processing in brain and machine: Evidence from EMEG and RSA

Li Su, Andrew Thwaites, William D. Marslen-Wilson, 2016 .

Improved neural network based language modelling and adaptation

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

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.

Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem

Andrew Thwaites, William D. Marslen-Wilson, Chao Zhang, 2017, bioRxiv.

The RT04 evaluation structural metadata systems at CUED

Marcus Tomalin, Philip C. Woodland, 2004 .

Morphological decomposition in Arabic ASR systems

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

Speaker Diarisation Using 2D Self-attentive Combination of Embeddings

Chao Zhang, Philip C. Woodland, Guangzhi Sun, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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).

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).

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

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

A One Pass Decoder Design For Large Vocabulary Recognition

Steve J. Young, Philip C. Woodland, V. Valtchev, 1994, HLT.

THE CU-HTK MARCH 2000 HUB5E TRANSCRIPTION SYSTEM

Thomas Hain, Gunnar Evermann, Philip C. Woodland, 2000 .

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.

Detecting deletions in ASR output

Philip C. Woodland, Matthew Stephen Seigel, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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.

Variable-length category-based n-grams for language modelling

Philip C. Woodland, Thomas Niesler, 1995 .

Porting: SwitchBoard to the VoiceMail task

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

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).

Improvements in accuracy and speed in the HTK broadcast news transcription system

Thomas Niesler, Thomas Hain, Philip C. Woodland, 1999, EUROSPEECH.

Complementary Phone Error Training

Philip C. Woodland, Frank Diehl, 2012, INTERSPEECH.

Comparison of language modelling techniques for Russian and English

Philip C. Woodland, Edward W. D. Whittaker, 1998, ICSLP.

Discriminatively Trained Gaussian Mixture Models for Sentence Boundary Detection

Marcus Tomalin, Philip C. Woodland, P. Woodland, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A wave digital filter model of the entire auditory periphery

Philip C. Woodland, Christian Giguere, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Multilingual large vocabulary speech recognition: the European SQALE project

David A. van Leeuwen, Jean-Luc Gauvain, Lori Lamel, 1997, Comput. Speech Lang..

The Cambridge University March 2005 speaker diarisation system

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

The Cambridge University Multimedia Document Retrieval Demo System

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 2001, Int. J. Speech Technol..

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)..

Modelling sub-phone insertions and deletions in continuous speech recognition

Thomas Hain, Philip C. Woodland, 2000, INTERSPEECH.

Effects of out of vocabulary words in spoken document retrieval (poster session)

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 2000, SIGIR '00.

Large vocabulary decoding and confidence estimation using word posterior probabilities

Gunnar Evermann, Philip C. Woodland, P. Woodland, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

A dynamic network decoder design for large vocabulary speech recognition

Steve Young, Philip C. Woodland, Jj Odell, 1994 .

A confidence-based approach for improving keyword hypothesis scores

Mark J. F. Gales, Philip C. Woodland, Matthew Stephen Seigel, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Segmentation and classification of broadcast news audio

Thomas Hain, Philip C. Woodland, 1998, ICSLP.

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

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

A variable-length category-based n-gram language model

Thomas Niesler, Philip C. Woodland, P. Woodland, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

The CUHTK-entropic 10xRT broadcast news transcription system

Thomas Hain, Philip C. Woodland, Jj Odell, 1999 .

Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models

Philip C. Woodland, S. M. Ahadi, 1997, Comput. Speech Lang..

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..

Morphological analysis and decomposition for Arabic speech-to-text systems

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2009, INTERSPEECH.

Modelling syllable characteristics to improve a large vocabulary continuous speech recogniser

Philip C. Woodland, M. Jones, 1994, ICSLP.

Using accent-specific pronunciation modelling for improved large vocabulary continuous speech recognition

Philip C. Woodland, Jason J. Humphries, P. Woodland, 1997, EUROSPEECH.

Experiments in speaker normalisation and adaptation for large vocabulary speech recognition

Philip C. Woodland, David Pye, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Data underpining "System Combination with Log-linear Models"

Mark J. F. Gales, Anton Ragni, Philip C. Woodland, 2016 .

Information Retrieval from Unsegmented Broadcast News Audio

Karen Spärck Jones, Philip C. Woodland, Pierre Jourlin, 2001, Int. J. Speech Technol..

Development of the 2003 CU-HTK conversational telephone speech transcription system

Mark J. F. Gales, Lan Wang, Thomas Hain, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

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).

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.

The use of prosody in a combined system for punctuation generation and speech recognition

Ji-Hwan Kim, Philip C. Woodland, 2001, INTERSPEECH.

A high-performance Cantonese keyword search system

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

Benchmark DARPA RM results using the HTK portable HMM toolkit

Steve Young, Philip C. Woodland, S. Young, 1992 .

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.

Recent developments in the HTK continuous speech recognition system

Steve Young, Philip C. Woodland, Jj Odell, 1994 .

Efficient generation and use of MLP features for Arabic speech recognition

Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland, 2009, INTERSPEECH.

Supplementary data for "Speaker Diarisation and Linking in Multi-Genre Broadcast Data"

Mark J. F. Gales, Chao Zhang, Pierre Lanchantin, 2015 .

Parameterised sigmoid and reLU hidden activation functions for DNN acoustic modelling

Chao Zhang, Philip C. Woodland, P. Woodland, 2015, INTERSPEECH.

Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning

Philip C. Woodland, Chao Zhang, Dongcheng Jiang, 2021, Interspeech 2021.

Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition pdf

Philip C. Woodland, Chao Zhang, Guangzhi Sun, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition

Philip C. Woodland, Qiujia Li, Chao Zhang, 2021, SSRN Electronic Journal.

Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition pdf

Philip C. Woodland, Chao Zhang, Xianrui Zheng, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training

Chao Zhang, Philip C. Woodland, Adnan Haider, 2021, Neural Networks.

Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models

Philip C. Woodland, Qiujia Li, Xiaoyu Yang, 2021 .

Residual Energy-Based Models for End-to-End Speech Recognition pdf

Liangliang Cao, Philip C. Woodland, Qiujia Li, 2021, Interspeech 2021.

Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations

Chao Zhang, Philip C. Woodland, Wen Wu, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition pdf

Philip C. Woodland, Qiujia Li, David Qiu, 2021, ArXiv.

DEVELOPING KEYWORD SEARCH UNDER THE IARPA BABEL PROGRAM

Xiaodong Cui, Brian Kingsbury, Bhuvana Ramabhadran, 2013 .

Network representation of the middle and inner ear in a composite model of the auditory periphery

Philip C. Woodland, Christian Giguère, 1992 .

Weight limiting, weight quantisation and generalisation in multi-layer perceptrons

Philip C. Woodland, 1989 .

Recent developments at Cambridge in broadcast news transcription

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