| 2026 | ACL | Protecting Bystander Privacy via Selective Hearing in Audio LLMs. | Xiao Zhan, Guangzhi Sun, Jose Such, Philip C. Woodland |
| 2025 | ACL | SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation. | Keqi Deng, Wenxi Chen, Xie Chen, Philip C. Woodland |
| 2025 | ACL | SkillAggregation: Reference-free LLM-Dependent Aggregation. | Guangzhi Sun, Anmol Kagrecha, Potsawee Manakul, Philip C. Woodland, Mark J. F. Gales |
| 2025 | ACL | DNCASR: End-to-End Training for Speaker-Attributed ASR. | Xianrui Zheng, Chao Zhang, Philip C. Woodland |
| 2025 | ICASSP | Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition. | Keqi Deng, Jinxi Guo, Yingyi Ma, Niko Moritz, Philip C. Woodland, Ozlem Kalinli, Mike Seltzer |
| 2025 | ICML | CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models. | Guangzhi Sun, Xiao Zhan, Shutong Feng, Philip C. Woodland, Jose Such |
| 2025 | NAACL | Wav2Prompt: End-to-End Speech Prompt Learning and Task-based Fine-tuning for Text-based LLMs. | Keqi Deng, Guangzhi Sun, Philip C. Woodland |
| 2024 | ACL | Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation. | Keqi Deng, Philip C. Woodland |
| 2024 | ACL | Speech-based Slot Filling using Large Language Models. | Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gasic, Philip C. Woodland |
| 2024 | ACL | Modelling Variability in Human Annotator Simulation. | Wen Wu, Wenlin Chen, Chao Zhang, Philip C. Woodland |
| 2024 | ACL | Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation. | Wen Wu, Bo Li, Chao Zhang, Chung-Cheng Chiu, Qiujia Li, Junwen Bai, Tara N. Sainath, Philip C. Woodland |
| 2024 | ICASSP | FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training. | Keqi Deng, Philip C. Woodland |
| 2024 | ICASSP | Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation. | Nineli Lashkarashvili, Wen Wu, Guangzhi Sun, Philip C. Woodland |
| 2024 | Interspeech | Confidence Estimation for Automatic Detection of Depression and Alzheimer's Disease Based on Clinical Interviews. | Wen Wu, Chao Zhang, Philip C. Woodland |
| 2024 | Interspeech | SOT Triggered Neural Clustering for Speaker Attributed ASR. | Xianrui Zheng, Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2023 | ACL | Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression. | Wen Wu, Chao Zhang, Philip C. Woodland |
| 2023 | ICASSP | Adaptable End-to-End ASR Models Using Replaceable Internal LMs and Residual Softmax. | Keqi Deng, Philip C. Woodland |
| 2023 | ICASSP | Spectral Clustering-Aware Learning of Embeddings for Speaker Diarisation. | Evonne P. C. Lee, Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2023 | ICASSP | Self-Supervised Learning-Based Source Separation for Meeting Data. | Yuang Li, Xianrui Zheng, Philip C. Woodland |
| 2023 | ICASSP | End-to-End Spoken Language Understanding with Tree-Constrained Pointer Generator. | Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2023 | ICASSP | Self-Supervised Representations in Speech-Based Depression Detection. | Wen Wu, Chao Zhang, Philip C. Woodland |
| 2023 | Interspeech | A Neural Time Alignment Module for End-to-End Automatic Speech Recognition. | Dongcheng Jiang, Chao Zhang, Philip C. Woodland |
| 2023 | Interspeech | Biased Self-supervised Learning for ASR. | Florian L. Kreyssig, Yangyang Shi, Jinxi Guo, Leda Sari, Abdel-rahman Mohamed, Philip C. Woodland |
| 2023 | Interspeech | Can Contextual Biasing Remain Effective with Whisper and GPT-2? | Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland |
| 2023 | Interspeech | Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations. | Wen Wu, Chao Zhang, Philip C. Woodland |
| 2022 | ICASSP | Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition. | Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland |
| 2022 | ICASSP | Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-Trained Models. | Xiaoyu Yang, Qiujia Li, Philip C. Woodland |
| 2022 | Interspeech | Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition. | Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2022 | Interspeech | Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription. | Xianrui Zheng, Chao Zhang, Philip C. Woodland |
| 2021 | ASRU | Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition. | Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2021 | ASRU | Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition. | Xianrui Zheng, Chao Zhang, Philip C. Woodland |
| 2021 | ICASSP | Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition. | Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman |
| 2021 | ICASSP | Transformer Language Models with LSTM-Based Cross-Utterance Information Representation. | Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2021 | ICASSP | Content-Aware Speaker Embeddings for Speaker Diarisation. | Guangzhi Sun, D. Liu, Chao Zhang, Philip C. Woodland |
| 2021 | ICASSP | Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations. | Wen Wu, Chao Zhang, Philip C. Woodland |
| 2021 | Interspeech | Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning. | Dongcheng Jiang, Chao Zhang, Philip C. Woodland |
| 2021 | Interspeech | Residual Energy-Based Models for End-to-End Speech Recognition. | Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland |
| 2020 | ICASSP | Improved Large-Margin Softmax Loss for Speaker Diarisation. | Yassir Fathullah, Chao Zhang, Philip C. Woodland |
| 2020 | Interspeech | Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings. | Florian L. Kreyssig, Philip C. Woodland |
| 2019 | ASRU | Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition. | Qiujia Li, Chao Zhang, Philip C. Woodland |
| 2019 | ICASSP | Speaker Diarisation Using 2D Self-attentive Combination of Embeddings. | Guangzhi Sun, Chao Zhang, Philip C. Woodland |
| 2019 | ICASSP | PyHTK: Python Library and ASR Pipelines for HTK. | Chao Zhang, Florian L. Kreyssig, Qiujia Li, Philip C. Woodland |
| 2019 | Interspeech | Multi-Span Acoustic Modelling Using Raw Waveform Signals. | Patrick von Platen, Chao Zhang, Philip C. Woodland |
| 2018 | ICASSP | Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS. | Florian L. Kreyssig, Chao Zhang, Philip C. Woodland |
| 2018 | ICASSP | High Order Recurrent Neural Networks for Acoustic Modelling. | Chao Zhang, Philip C. Woodland |
| 2018 | Interspeech | Combining Natural Gradient with Hessian Free Methods for Sequence Training. | Adnan Haider, Philip C. Woodland |
| 2018 | Interspeech | Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems. | Yu Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland |
| 2018 | Interspeech | Semi-tied Units for Efficient Gating in LSTM and Highway Networks. | Chao Zhang, Philip C. Woodland |
| 2017 | ASRU | Sequence training of DNN acoustic models with natural gradient. | Adnan Haider, Philip C. Woodland |
| 2017 | ICASSP | Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training. | Chao Zhang, Philip C. Woodland |
| 2016 | ICASSP | CUED-RNNLM - An open-source toolkit for efficient training and evaluation of recurrent neural network language models. | Xie Chen, Xunying Liu, Y. Qian, Mark J. F. Gales, Philip C. Woodland |
| 2016 | ICASSP | Improved DNN-based segmentation for multi-genre broadcast audio. | Linlin Wang, Chao Zhang, Philip C. Woodland, Mark J. F. Gales, Panagiota Karanasou, Pierre Lanchantin, Xunying Liu, Yanmin Qian |
| 2016 | ICASSP | System combination with log-linear models. | J. Yang, Chao Zhang, Anton Ragni, Mark J. F. Gales, Philip C. Woodland |
| 2016 | ICASSP | DNN speaker adaptation using parameterised sigmoid and ReLU hidden activation functions. | Chao Zhang, Philip C. Woodland |
| 2016 | Interspeech | Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems. | Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanman Qian, Linlin Wang, Philip C. Woodland, Chao Zhang |
| 2015 | ASRU | The MGB challenge: Evaluating multi-genre broadcast media recognition. | Peter Bell, Mark J. F. Gales, Thomas Hain, Jonathan Kilgour, Pierre Lanchantin, Xunying Liu, Andrew McParland, Steve Renals, Oscar Saz, Mirjam Wester, Philip C. Woodland |
| 2015 | ASRU | Investigation of back-off based interpolation between recurrent neural network and n-gram language models. | Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2015 | ASRU | Multilingual representations for low resource speech recognition and keyword search. | Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, Abhinav Sethy, Kartik Audhkhasi, Xiaodong Cui, Ellen Kislal, Lidia Mangu, Markus Nubaum-Thom, Michael Picheny, Zoltn Tske, Pavel Golik, Ralf Schlter, Hermann Ney, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang, Philip C. Woodland |
| 2015 | ASRU | Speaker diarisation and longitudinal linking in multi-genre broadcast data. | Penny Karanasou, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang |
| 2015 | ASRU | The development of the cambridge university alignment systems for the multi-genre broadcast challenge. | Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang |
| 2015 | ASRU | Cambridge university transcription systems for the multi-genre broadcast challenge. | Philip C. Woodland, Xunying Liu, Yanmin Qian, Chao Zhang, Mark J. F. Gales, Penny Karanasou, Pierre Lanchantin, Linlin Wang |
| 2015 | ICASSP | Improving the training and evaluation efficiency of recurrent neural network language models. | Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2015 | ICASSP | Recurrent neural network language model training with noise contrastive estimation for speech recognition. | Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2015 | ICASSP | Paraphrastic recurrent neural network language models. | Xunying Liu, Xie Chen, Mark J. F. Gales, Philip C. Woodland |
| 2015 | Interspeech | Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. | Xie Chen, Tian Tan, Xunying Liu, Pierre Lanchantin, M. Wan, Mark J. F. Gales, Philip C. Woodland |
| 2015 | Interspeech | I-vector estimation using informative priors for adaptation of deep neural networks. | Penny Karanasou, Mark J. F. Gales, Philip C. Woodland |
| 2015 | Interspeech | The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation. | Xunying Liu, Federico Flego, Linlin Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland |
| 2015 | Interspeech | Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages. | Haipeng Wang, Anton Ragni, Mark J. F. Gales, Kate M. Knill, Philip C. Woodland, Chao Zhang |
| 2015 | Interspeech | Parameterised sigmoid and reLU hidden activation functions for DNN acoustic modelling. | Chao Zhang, Philip C. Woodland |
| 2015 | Interspeech | A general artificial neural network extension for HTK. | Chao Zhang, Philip C. Woodland |
| 2014 | ICASSP | Paraphrastic neural network language models. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2014 | ICASSP | Efficient lattice rescoring using recurrent neural network language models. | Xunying Liu, Yongqiang Wang, Xie Chen, Mark J. F. Gales, Philip C. Woodland |
| 2014 | ICASSP | Detecting deletions in ASR output. | Matthew Stephen Seigel, Philip C. Woodland |
| 2014 | ICASSP | Direct sub-word confidence estimation with hidden-state conditional random fields. | Matthew Stephen Seigel, Philip C. Woodland |
| 2014 | ICASSP | Standalone training of context-dependent deep neural network acoustic models. | Chao Zhang, Philip C. Woodland |
| 2014 | Interspeech | Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch. | Xie Chen, Yongqiang Wang, Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2014 | Interspeech | Adaptation of deep neural network acoustic models using factorised i-vectors. | Penny Karanasou, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland |
| 2013 | ASRU | Investigation of multilingual deep neural networks for spoken term detection. | Kate M. Knill, Mark J. F. Gales, Shakti P. Rath, Philip C. Woodland, Chao Zhang, Shi-Xiong Zhang |
| 2013 | ICASSP | A high-performance Cantonese keyword search system. | Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Kate M. Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlter, Abhinav Sethy, Philip C. Woodland |
| 2013 | ICASSP | Paraphrastic language models and combination with neural network language models. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2013 | ICASSP | System combination and score normalization for spoken term detection. | Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Brian Kingsbury, Kate M. Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlter, Abhinav Sethy, Philip C. Woodland |
| 2013 | ICASSP | A confidence-based approach for improving keyword hypothesis scores. | Matthew Stephen Seigel, Philip C. Woodland, Mark J. F. Gales |
| 2013 | Interspeech | Automatic Transcription of Multi-genre Media Archives. | Pierre Lanchantin, Peter Bell, Mark J. F. Gales, Thomas Hain, Xunying Liu, Yanhua Long, Jennifer Quinnell, Steve Renals, Oscar Saz, Matthew Stephen Seigel, Pawel Swietojanski, Philip C. Woodland |
| 2013 | Interspeech | Cross-domain paraphrasing for improving language modelling using out-of-domain data. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2013 | Interspeech | Improving lightly supervised training for broadcast transcription. | Yanhua Long, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Matthew Stephen Seigel, Philip C. Woodland |
| 2012 | Interspeech | Complementary Phone Error Training. | Frank Diehl, Philip C. Woodland |
| 2012 | Interspeech | Paraphrastic Language Models. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2012 | Interspeech | Using Sub-word-level Information for Confidence Estimation with Conditional Random Field Models. | Matthew Stephen Seigel, Philip C. Woodland |
| 2011 | ICASSP | Investigation of acoustic units for LVCSR systems. | Xunying Liu, Mark John Francis Gales, Jim L. Hieronymus, Philip C. Woodland |
| 2011 | Interspeech | Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems. | Frank Diehl, Mark John Francis Gales, Xunying Liu, Marcus Tomalin, Philip C. Woodland |
| 2011 | Interspeech | Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2011 | Interspeech | Graphone Model Interpolation and Arabic Pronunciation Generation. | T. Li, Philip C. Woodland, Frank Diehl, Mark J. F. Gales |
| 2011 | Interspeech | Combining Information Sources for Confidence Estimation with CRF Models. | Matthew Stephen Seigel, Philip C. Woodland |
| 2010 | ICASSP | Language model combination and adaptation usingweighted finite state transducers. | Xunying Liu, Mark J. F. Gales, Jim L. Hieronymus, Philip C. Woodland |
| 2010 | ICASSP | Recent improvements to the Cambridge Arabic Speech-to-Text systems. | Marcus Tomalin, Frank Diehl, Mark J. F. Gales, Junho Park, Philip C. Woodland |
| 2010 | Interspeech | Language model cross adaptation for LVCSR system combination. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2010 | Interspeech | Improved neural network based language modelling and adaptation. | Junho Park, Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2009 | ICASSP | Training and adapting MLP features for Arabic speech recognition. | Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland |
| 2009 | Interspeech | Morphological analysis and decomposition for Arabic speech-to-text systems. | Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland |
| 2009 | Interspeech | Exploiting Chinese character models to improve speech recognition performance. | Jim L. Hieronymus, Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2009 | Interspeech | Use of contexts in language model interpolation and adaptation. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2009 | Interspeech | Efficient generation and use of MLP features for Arabic speech recognition. | Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland |
| 2008 | ICASSP | Phonetic pronunciations for arabic speech-to-text systems. | Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland |
| 2008 | ICASSP | Unsupervised discriminative adaptation using discriminative mapping transforms. | Kai Yu, Mark J. F. Gales, Philip C. Woodland |
| 2008 | Interspeech | Context dependent language model adaptation. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2007 | ASRU | Development of a phonetic system for large vocabulary Arabic speech recognition. | Mark J. F. Gales, Frank Diehl, Chandra Kant Raut, Marcus Tomalin, Philip C. Woodland, Kai Yu |
| 2007 | ASRU | Discriminative language model adaptation for Mandarin broadcast speech transcription and translation. | Xunying Liu, William J. Byrne, Mark J. F. Gales, Adri de Gispert, Marcus Tomalin, Philip C. Woodland, Kai Yu |
| 2007 | ICASSP | Speech Recognition System Combination for Machine Translation. | Mark J. F. Gales, Xunying Liu, Rohit Sinha, Philip C. Woodland, Kai Yu, Spyros Matsoukas, Tim Ng, Kham Nguyen, Long Nguyen, Jean-Luc Gauvain, Lori Lamel, Abdelkhalek Messaoudi |
| 2007 | ICASSP | Consensus Network Decoding for Statistical Machine Translation System Combination. | Khe Chai Sim, William J. Byrne, Mark J. F. Gales, Hichem Sahbi, Philip C. Woodland |
| 2007 | ICASSP | Improving Speech Transcription for Mandarin-English Translation. | Marcus Tomalin, Mark J. F. Gales, X. Andrew Liu, Khe Chai Sim, Rohit Sinha, Lan Wang, Philip C. Woodland, Kai Yu |
| 2007 | ICASSP | Unsupervised Training for Mandarin Broadcast News and Conversation Transcription. | Lan Wang, Mark J. F. Gales, Philip C. Woodland |
| 2007 | Interspeech | Unsupervised training with directed manual transcription for recognising Mandarin broadcast audio. | Kai Yu, Mark J. F. Gales, Philip C. Woodland |
| 2006 | ICASSP | The Cu-Htk Mandarin Broadcast News Transcription System. | Rohit Sinha, Mark J. F. Gales, Do Yeong Kim, X. Andrew Liu, Khe Chai Sim, Philip C. Woodland |
| 2006 | ICASSP | Discriminatively Trained Gaussian Mixture Models for Sentence Boundary Detection. | Marcus Tomalin, Philip C. Woodland |
| 2006 | Interspeech | Unsupervised language model adaptation for Mandarin broadcast conversation transcription. | David Mrva, Philip C. Woodland |
| 2005 | ICASSP | Training LVCSR Systems on Thousands of Hours of Data. | Gunnar Evermann, Ho Yin Chan, Mark J. F. Gales, Bin Jia, David Mrva, Philip C. Woodland, Kai Yu |
| 2005 | ICASSP | Development of the CUHTK 2004 Mandarin Conversational Telephone Speech Transcription System. | Mark J. F. Gales, Bin Jia, X. Andrew Liu, Khe Chai Sim, Philip C. Woodland, Kai Yu |
| 2005 | ICASSP | Development of the CU-HTK 2004 Broadcast News Transcription Systems. | Do Yeong Kim, Ho Yin Chan, Gunnar Evermann, Mark J. F. Gales, David Mrva, Khe Chai Sim, Philip C. Woodland |
| 2005 | ICASSP | Structural metadata research in the EARS program. | Yang Liu, Elizabeth Shriberg, Andreas Stolcke, Barbara Peskin, Jeremy Ang, Dustin Hillard, Mari Ostendorf, Marcus Tomalin, Philip C. Woodland, Mary P. Harper |
| 2005 | Interspeech | The Cambridge University March 2005 speaker diarisation system. | Rohit Sinha, S. E. Tranter, Mark J. F. Gales, Philip C. Woodland |
| 2004 | ICASSP | Improving broadcast news transcription by lightly supervised discriminative training. | Ho Yin Chan, Philip C. Woodland |
| 2004 | ICASSP | Development of the 2003 CU-HTK conversational telephone speech transcription system. | Gunnar Evermann, Ho Yin Chan, Mark J. F. Gales, Thomas Hain, Xunying Liu, David Mrva, Lan Wang, Philip C. Woodland |
| 2004 | ICASSP | Generating and evaluating segmentations for automatic speech recognition of conversational telephone speech. | Sue Tranter, Kai Yu, Gunnar Evermann, Philip C. Woodland |
| 2004 | ICASSP | MPE-based discriminative linear transform for speaker adaptation. | Lan Wang, Philip C. Woodland |
| 2004 | Interspeech | Using VTLN for broadcast news transcription. | Do Yeong Kim, Srinivasan Umesh, Mark J. F. Gales, Thomas Hain, Philip C. Woodland |
| 2004 | Interspeech | A PLSA-based language model for conversational telephone speech. | David Mrva, Philip C. Woodland |
| 2003 | ICASSP | Porting: SwitchBoard to the VoiceMail task. | Mark J. F. Gales, Yuan Dong, Daniel Povey, Philip C. Woodland |
| 2003 | ICASSP | Automatic complexity control for HLDA systems. | Xunying Liu, Mark J. F. Gales, Philip C. Woodland |
| 2003 | ICASSP | Discriminative map for acoustic model adaptation. | Daniel Povey, Philip C. Woodland, Mark J. F. Gales |
| 2003 | Interspeech | MMI-MAP and MPE-MAP for acoustic model adaptation. | Daniel Povey, Mark J. F. Gales, Do Yeong Kim, Philip C. Woodland |
| 2002 | ICASSP | Improved cross-task recognition using MMIE training. | Ricardo de Crdoba, Philip C. Woodland, Mark J. F. Gales |
| 2002 | ICASSP | Implementation of automatic capitalisation generation systems for speech input. | Ji-Hwan Kim, Philip C. Woodland |
| 2002 | ICASSP | Minimum Phone Error and I-smoothing for improved discriminative training. | Daniel Povey, Philip C. Woodland |
| 2002 | Interspeech | Maximum mutual information training of hidden Markov models with vector linear predictors. | K. K. Chin, Philip C. Woodland |
| 2002 | Interspeech | Cluster identification for speaker-environment tracking. | J. T. Wickramaratna, Philip C. Woodland |
| 2001 | ICASSP | New features in the CU-HTK system for transcription of conversational telephone speech. | Thomas Hain, Philip C. Woodland, Gunnar Evermann, Daniel Povey |
| 2001 | ICASSP | Improved discriminative training techniques for large vocabulary continuous speech recognition. | Daniel Povey, Philip C. Woodland |
| 2001 | ICASSP | Improvements in linear transform based speaker adaptation. | Lus Felipe Uebel, Philip C. Woodland |
| 2001 | ICASSP | Efficient class-based language modelling for very large vocabularies. | Edward W. D. Whittaker, Philip C. Woodland |
| 2001 | Interspeech | The use of prosody in a combined system for punctuation generation and speech recognition. | Ji-Hwan Kim, Philip C. Woodland |
| 2000 | ICASSP | Large vocabulary decoding and confidence estimation using word posterior probabilities. | Gunnar Evermann, Philip C. Woodland |
| 2000 | ICASSP | A method for direct audio search with applications to indexing and retrieval. | Sue E. Johnson, Philip C. Woodland |
| 2000 | Interspeech | Modelling sub-phone insertions and deletions in continuous speech recognition. | Thomas Hain, Philip C. Woodland |
| 2000 | Interspeech | A rule-based named entity recognition system for speech input. | Ji-Hwan Kim, Philip C. Woodland |
| 2000 | Interspeech | Particle-based language modelling. | Edward W. D. Whittaker, Philip C. Woodland |
| 2000 | SIGIR | The Cambridge University multimedia document retrieval demo system. | Andreas Tuerk, Sue E. Johnson, Pierre Jourlin, Karen Sparck Jones, Philip C. Woodland |
| 2000 | SIGIR | Effects of out of vocabulary words in spoken document retrieval. | Philip C. Woodland, Sue E. Johnson, Pierre Jourlin, Karen Sparck Jones |
| 1999 | ICASSP | The 1998 HTK system for transcription of conversational telephone speech. | Thomas Hain, Philip C. Woodland, Thomas Niesler, Edward W. D. Whittaker |
| 1999 | ICASSP | The Cambridge University spoken document retrieval system. | Sue E. Johnson, Pierre Jourlin, Gareth L. Moore, Karen Sprck Jones, Philip C. Woodland |
| 1999 | ICASSP | Frame discrimination training for HMMs for large vocabulary speech recognition. | Daniel Povey, Philip C. Woodland |
| 1999 | Interspeech | Dynamic HMM selection for continuous speech recognition. | Thomas Hain, Philip C. Woodland |
| 1999 | Interspeech | An investigation into vocal tract length normalisation. | Lus Felipe Uebel, Philip C. Woodland |
| 1999 | Interspeech | Improvements in accuracy and speed in the HTK broadcast news transcription system. | Philip C. Woodland, J. J. Odell, Thomas Hain, Gareth L. Moore, Thomas Niesler, Andreas Tuerk, Edward W. D. Whittaker |
| 1999 | SIGIR | Improving Retrieval on Imperfect Speech Transcriptions (poster abstract). | Pierre Jourlin, Sue E. Johnson, Karen Sparck Jones, Philip C. Woodland |
| 1998 | ICASSP | The use of accent-specific pronunciation dictionaries in acoustic model training. | Jason J. Humphries, Philip C. Woodland |
| 1998 | ICASSP | Comparison of part-of-speech and automatically derived category-based language models for speech recognition. | Thomas Niesler, Edward W. D. Whittaker, Philip C. Woodland |
| 1998 | ICASSP | Experiments in broadcast news transcription. | Philip C. Woodland, Thomas Hain, Sue E. Johnson, Thomas Niesler, Andreas Tuerk, Steve J. Young |
| 1998 | Interspeech | Segmentation and classification of broadcast news audio. | Thomas Hain, Philip C. Woodland |
| 1998 | Interspeech | Speaker clustering using direct maximisation of the MLLR-adapted likelihood. | Sue E. Johnson, Philip C. Woodland |
| 1998 | Interspeech | Comparison of language modelling techniques for Russian and English. | Edward W. D. Whittaker, Philip C. Woodland |
| 1997 | ICASSP | Modelling word-pair relations in a category-based language model. | Thomas Niesler, Philip C. Woodland |
| 1997 | ICASSP | Experiments in speaker normalisation and adaptation for large vocabulary speech recognition. | David Pye, Philip C. Woodland |
| 1997 | ICASSP | Broadcast news transcription using HTK. | Philip C. Woodland, Mark J. F. Gales, David Pye, Steve J. Young |
| 1997 | Interspeech | Using accent-specific pronunciation modelling for improved large vocabulary continuous speech recognition. | Jason J. Humphries, Philip C. Woodland |
| 1996 | ICASSP | A variable-length category-based n-gram language model. | Thomas Niesler, Philip C. Woodland |
| 1996 | ICASSP | Lattice-based discriminative training for large vocabulary speech recognition. | Valtcho Valtchev, Julian Odell, Philip C. Woodland, Steve J. Young |
| 1996 | ICASSP | Improving environmental robustness in large vocabulary speech recognition. | Philip C. Woodland, Mark John Francis Gales, David Pye |
| 1996 | Interspeech | Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation. | Mark J. F. Gales, David Pye, Philip C. Woodland |
| 1996 | Interspeech | Using accent-specific pronunciation modelling for robust speech recognition. | Jason J. Humphries, Philip C. Woodland, David J. B. Pearce |
| 1996 | Interspeech | Combination of word-based and category-based language models. | Thomas Niesler, Philip C. Woodland |
| 1996 | Interspeech | Discriminative optimisation of large vocabulary recognition systems. | V. Valtchev, Philip C. Woodland, Steve J. Young |
| 1996 | Interspeech | Iterative unsupervised adaptation using maximum likelihood linear regression. | Philip C. Woodland, David Pye, Mark J. F. Gales |
| 1995 | ICASSP | Rapid speaker adaptation using model prediction. | S. M. Ahadi, Philip C. Woodland |
| 1995 | ICASSP | Automatic speech synthesiser parameter estimation using HMMs. | Robert E. Donovan, Philip C. Woodland |
| 1995 | ICASSP | The 1994 HTK large vocabulary speech recognition system. | Philip C. Woodland, C. J. Leggetter, Julian Odell, Valtcho Valtchev, Steve J. Young |
| 1995 | Interspeech | Improvements in an HMM-based speech synthesiser. | Robert E. Donovan, Philip C. Woodland |
| 1995 | Interspeech | Flexible speaker adaptation for large vocabulary speech recognition. | C. J. Leggetter, Philip C. Woodland |
| 1995 | Interspeech | Large vocabulary multilingual speech recognition using HTK. | David Pye, Philip C. Woodland, Steve J. Young |
| 1994 | ICASSP | Large vocabulary continuous speech recognition using HTK. | Philip C. Woodland, J. J. Odell, V. Valtchev, Steve J. Young |
| 1994 | Interspeech | Modelling syllable characteristics to improve a large vocabulary continuous speech recogniser. | M. Jones, Philip C. Woodland |
| 1994 | Interspeech | Speaker adaptation of continuous density HMMs using multivariate linear regression. | C. J. Leggetter, Philip C. Woodland |
| 1994 | Interspeech | Recognition ********* a dynamic network decoder design for large vocabulary speech recognition. | V. Valtchev, J. J. Odell, Philip C. Woodland, Steve J. Young |
| 1994 | NAACL | A One Pass Decoder Design For Large Vocabulary Recognition. | J. J. Odell, V. Valtchev, Philip C. Woodland, Steve J. Young |
| 1994 | NAACL | Tree-Based State Tying for High Accuracy Modelling. | Steve J. Young, J. J. Odell, Philip C. Woodland |
| 1993 | ICASSP | A wave digital filter model of the entire auditory periphery. | Christian Gigure, Philip C. Woodland |
| 1993 | ICASSP | Exploiting variable-width features in large vocabulary speech recognition. | M. Jones, Philip C. Woodland |
| 1993 | Interspeech | Using relative duration in large vocabulary speech recognition. | M. Jones, Philip C. Woodland |
| 1993 | Interspeech | Hidden Markov models using shared vector linear predictors. | B. A. Maxwell, Philip C. Woodland |
| 1993 | Interspeech | The HTK tied-state continuous speech recogniser. | Philip C. Woodland, Steve J. Young |
| 1993 | Interspeech | The use of state tying in continuous speech recognition. | Steve J. Young, Philip C. Woodland |
| 1992 | ICASSP | Hidden Markov models using vector linear prediction and discriminative output distributions. | Philip C. Woodland |
| 1991 | ICASSP | Optimising hidden Markov models using discriminative output distributions. | Philip C. Woodland, David R. Cole |