Philip C. Woodland

310 papers A* 5A 52C 13Misc 68Journal 108Unranked 64

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Measuring the Redundancy of Decoder Layers in SpeechLLMs. CoRR Adel Moumen, Guangzhi Sun, Philip C. Woodland
2025	J	`jnl`	Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processing. CoRR Mengqi Wang, Zhan Liu, Zengrui Jin, Guangzhi Sun, Chao Zhang, Philip C. Woodland
2025	A*	`conf`	CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models. ICML Guangzhi Sun, Xiao Zhan, Shutong Feng, Philip C. Woodland, Jose Such
2025	J	`jnl`	CASE-Bench: Context-Aware Safety Evaluation Benchmark for Large Language Models. CoRR Guangzhi Sun, Xiao Zhan, Shutong Feng, Philip C. Woodland, Jose Such
2025	J	`jnl`	Cross-Lingual Interleaving for Speech Language Models. CoRR Adel Moumen, Guangzhi Sun, Philip C. Woodland
2025	—	`conf`	DNCASR: End-to-End Training for Speaker-Attributed ASR. ACL (1) Xianrui Zheng, Chao Zhang, Philip C. Woodland
2025	J	`jnl`	Discrete Audio Tokens: More Than a Survey! CoRR Pooneh Mousavi, Gallil Maimon, Adel Moumen, Darius Petermann, Jiatong Shi, Haibin Wu, Haici Yang, Anastasia Kuznetsova, Artem Ploujnikov, Ricard Marxer, Bhuvana Ramabhadran, Benjamin Elizalde, Loren Lugosch, Jinyu Li, Cem Subakan, Philip C. Woodland, Minje Kim, Hung-yi Lee, Shinji Watanabe, Yossi Adi, Mirco Ravanelli
2025	J	`jnl`	Discrete Audio Tokens: More Than a Survey! Trans. Mach. Learn. Res. Pooneh Mousavi, Gallil Maimon, Adel Moumen, Darius Petermann, Jiatong Shi, Haibin Wu, Haici Yang, Anastasia Kuznetsova, Artem Ploujnikov, Ricard Marxer, Bhuvana Ramabhadran, Benjamin Elizalde, Loren Lugosch, Jinyu Li, Cem Subakan, Philip C. Woodland, Minje Kim, Hung-yi Lee, Shinji Watanabe, Yossi Adi, Mirco Ravanelli
2025	J	`jnl`	Knowledge-aware audio-grounded generative slot filling for limited annotated data. Comput. Speech Lang. Guangzhi Sun, Chao Zhang, Ivan Vulic, Pawel Budzianowski, Philip C. Woodland
2025	J	`jnl`	Multi-head Temporal Latent Attention. CoRR Keqi Deng, Philip C. Woodland
2025	J	`jnl`	Protecting Bystander Privacy via Selective Hearing in Audio LLMs. CoRR Xiao Zhan, Guangzhi Sun, Jose Such, Philip C. Woodland
2025	—	`conf`	SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation. ACL (1) Keqi Deng, Wenxi Chen, Xie Chen, Philip C. Woodland
2025	J	`jnl`	SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation. CoRR Keqi Deng, Wenxi Chen, Xie Chen, Philip C. Woodland
2025	—	`conf`	SkillAggregation: Reference-free LLM-Dependent Aggregation. ACL (1) Guangzhi Sun, Anmol Kagrecha, Potsawee Manakul, Philip C. Woodland, Mark J. F. Gales
2025	Misc	`conf`	Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition. ICASSP Keqi Deng, Jinxi Guo, Yingyi Ma, Niko Moritz, Philip C. Woodland, Ozlem Kalinli, Mike Seltzer
2025	—	`conf`	Wav2Prompt: End-to-End Speech Prompt Learning and Task-based Fine-tuning for Text-based LLMs. NAACL (Long Papers) Keqi Deng, Guangzhi Sun, Philip C. Woodland
2024	—	`conf`	1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem. Odyssey Mingjie Chen, Hezhao Zhang, Yuanchao Li, Jiachen Luo, Wen Wu, Ziyang Ma, Peter Bell, Catherine Lai, Joshua D. Reiss, Lin Wang, Philip C. Woodland, Xie Chen, Huy Phan, Thomas Hain
2024	J	`jnl`	1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem. CoRR Mingjie Chen, Hezhao Zhang, Yuanchao Li, Jiachen Luo, Wen Wu, Ziyang Ma, Peter Bell, Catherine Lai, Joshua D. Reiss, Lin Wang, Philip C. Woodland, Xie Chen, Huy Phan, Thomas Hain
2024	A*	`conf`	An Improved Empirical Fisher Approximation for Natural Gradient Descent. NeurIPS Xiaodong Wu, Wenyi Yu, Chao Zhang, Philip C. Woodland
2024	J	`jnl`	An Improved Empirical Fisher Approximation for Natural Gradient Descent. CoRR Xiaodong Wu, Wenyi Yu, Chao Zhang, Philip C. Woodland
2024	—	`conf`	Automatic Time Alignment Generation For End-to-End ASR Using Acoustic Probability Modelling. SLT Dongcheng Jiang, Chao Zhang, Philip C. Woodland
2024	A	`conf`	Confidence Estimation for Automatic Detection of Depression and Alzheimer's Disease Based on Clinical Interviews. INTERSPEECH Wen Wu, Chao Zhang, Philip C. Woodland
2024	J	`jnl`	Confidence Estimation for Automatic Detection of Depression and Alzheimer's Disease Based on Clinical Interviews. CoRR Wen Wu, Chao Zhang, Philip C. Woodland
2024	J	`jnl`	CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models. CoRR Guangzhi Sun, Potsawee Manakul, Adian Liusie, Kunat Pipatanakul, Chao Zhang, Philip C. Woodland, Mark J. F. Gales
2024	J	`jnl`	Decoupled structure for improved adaptability of end-to-end models. Speech Commun. Keqi Deng, Philip C. Woodland
2024	Misc	`conf`	FastInject: Injecting Unpaired Text Data into CTC-Based ASR Training. ICASSP Keqi Deng, Philip C. Woodland
2024	J	`jnl`	Graph Neural Networks for Contextual ASR With the Tree-Constrained Pointer Generator. IEEE ACM Trans. Audio Speech Lang. Process. Guangzhi Sun, Chao Zhang, Philip C. Woodland
2024	—	`conf`	Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation. ACL (1) Wen Wu, Bo Li, Chao Zhang, Chung-Cheng Chiu, Qiujia Li, Junwen Bai, Tara N. Sainath, Philip C. Woodland
2024	J	`jnl`	Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation. CoRR Wen Wu, Bo Li, Chao Zhang, Chung-Cheng Chiu, Qiujia Li, Junwen Bai, Tara N. Sainath, Philip C. Woodland
2024	J	`jnl`	Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Keqi Deng, Philip C. Woodland
2024	—	`conf`	Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation. ACL (1) Keqi Deng, Philip C. Woodland
2024	J	`jnl`	Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation. CoRR Keqi Deng, Philip C. Woodland
2024	J	`jnl`	MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events. CoRR Xiaoyu Yang, Qiujia Li, Chao Zhang, Philip C. Woodland
2024	—	`conf`	Modelling Variability in Human Annotator Simulation. ACL (Findings) Wen Wu, Wenlin Chen, Chao Zhang, Philip C. Woodland
2024	Misc	`conf`	Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation. ICASSP Nineli Lashkarashvili, Wen Wu, Guangzhi Sun, Philip C. Woodland
2024	J	`jnl`	Parameter Efficient Finetuning for Speech Emotion Recognition and Domain Adaptation. CoRR Nineli Lashkarashvili, Wen Wu, Guangzhi Sun, Philip C. Woodland
2024	A	`conf`	SOT Triggered Neural Clustering for Speaker Attributed ASR. INTERSPEECH Xianrui Zheng, Guangzhi Sun, Chao Zhang, Philip C. Woodland
2024	J	`jnl`	SkillAggregation: Reference-free LLM-Dependent Aggregation. CoRR Guangzhi Sun, Anmol Kagrecha, Potsawee Manakul, Philip C. Woodland, Mark J. F. Gales
2024	—	`conf`	Speech-based Slot Filling using Large Language Models. ACL (Findings) Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gasic, Philip C. Woodland
2024	J	`jnl`	Transducer-Llama: Integrating LLMs into Streamable Transducer-based Speech Recognition. CoRR Keqi Deng, Jinxi Guo, Yingyi Ma, Niko Moritz, Philip C. Woodland, Ozlem Kalinli, Mike Seltzer
2024	J	`jnl`	Wav2Prompt: End-to-End Speech Prompt Generation and Tuning For LLM in Zero and Few-shot Learning. CoRR Keqi Deng, Guangzhi Sun, Philip C. Woodland
2023	A	`conf`	A Neural Time Alignment Module for End-to-End Automatic Speech Recognition. INTERSPEECH Dongcheng Jiang, Chao Zhang, Philip C. Woodland
2023	Misc	`conf`	Adaptable End-to-End ASR Models Using Replaceable Internal LMs and Residual Softmax. ICASSP Keqi Deng, Philip C. Woodland
2023	J	`jnl`	Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax. CoRR Keqi Deng, Philip C. Woodland
2023	A	`conf`	Biased Self-supervised Learning for ASR. INTERSPEECH Florian L. Kreyssig, Yangyang Shi, Jinxi Guo, Leda Sari, Abdel-rahman Mohamed, Philip C. Woodland
2023	A	`conf`	Can Contextual Biasing Remain Effective with Whisper and GPT-2? INTERSPEECH Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Can Contextual Biasing Remain Effective with Whisper and GPT-2? CoRR Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Combining hybrid DNN-HMM ASR systems with attention-based models using lattice rescoring. Speech Commun. Qiujia Li, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Conditional Diffusion Model for Target Speaker Extraction. CoRR Theodor Nguyen, Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Decoupled Structure for Improved Adaptability of End-to-End Models. CoRR Keqi Deng, Philip C. Woodland
2023	Misc	`conf`	End-to-End Spoken Language Understanding with Tree-Constrained Pointer Generator. ICASSP Guangzhi Sun, Chao Zhang, Philip C. Woodland
2023	—	`conf`	Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression. ACL (1) Wen Wu, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Estimating the Uncertainty in Emotion Attributes using Deep Evidential Regression. CoRR Wen Wu, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Estimating the Uncertainty in Emotion Class Labels With Utterance-Specific Dirichlet Priors. IEEE Trans. Affect. Comput. Wen Wu, Chao Zhang, Xixin Wu, Philip C. Woodland
2023	J	`jnl`	FastInject: Injecting Unpaired Text Data into CTC-based ASR training. CoRR Keqi Deng, Philip C. Woodland
2023	J	`jnl`	Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generator. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2023	A	`conf`	Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations. INTERSPEECH Wen Wu, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Integrating Emotion Recognition with Speech Recognition and Speaker Diarisation for Conversations. CoRR Wen Wu, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation. CoRR Wen Wu, Wenlin Chen, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition. CoRR Xiaoyu Yang, Qiujia Li, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data. CoRR Guangzhi Sun, Chao Zhang, Ivan Vulic, Pawel Budzianowski, Philip C. Woodland
2023	J	`jnl`	Minimising Biasing Word Errors for Contextual ASR With the Tree-Constrained Pointer Generator. IEEE ACM Trans. Audio Speech Lang. Process. Guangzhi Sun, Chao Zhang, Philip C. Woodland
2023	Misc	`conf`	Self-Supervised Learning-Based Source Separation for Meeting Data. ICASSP Yuang Li, Xianrui Zheng, Philip C. Woodland
2023	Misc	`conf`	Self-Supervised Representations in Speech-Based Depression Detection. ICASSP Wen Wu, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Self-supervised representations in speech-based depression detection. CoRR Wen Wu, Chao Zhang, Philip C. Woodland
2023	Misc	`conf`	Spectral Clustering-Aware Learning of Embeddings for Speaker Diarisation. ICASSP Evonne P. C. Lee, Guangzhi Sun, Chao Zhang, Philip C. Woodland
2023	J	`jnl`	Speech-based Slot Filling using Large Language Models. CoRR Guangzhi Sun, Shutong Feng, Dongcheng Jiang, Chao Zhang, Milica Gasic, Philip C. Woodland
2022	J	`jnl`	Biased Self-supervised learning for ASR. CoRR Florian L. Kreyssig, Yangyang Shi, Jinxi Guo, Leda Sari, Abdelrahman Mohamed, Philip C. Woodland
2022	—	`conf`	Distribution-Based Emotion Recognition in Conversation. SLT Wen Wu, Chao Zhang, Philip C. Woodland
2022	J	`jnl`	Distribution-based Emotion Recognition in Conversation. CoRR Wen Wu, Chao Zhang, Philip C. Woodland
2022	J	`jnl`	End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2022	J	`jnl`	Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors. CoRR Wen Wu, Chao Zhang, Xixin Wu, Philip C. Woodland
2022	Misc	`conf`	Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition. ICASSP Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland
2022	Misc	`conf`	Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-Trained Models. ICASSP Xiaoyu Yang, Qiujia Li, Philip C. Woodland
2022	J	`jnl`	Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2022	J	`jnl`	On the similarities of representations in artificial and brain neural networks for speech recognition. Frontiers Comput. Neurosci. Cai Wingfield, Chao Zhang, Barry Devereux, Elisabeth Fonteneau, Andrew Thwaites, Xunying Liu, Philip C. Woodland, William D. Marslen-Wilson, Li Su
2022	J	`jnl`	Spectral Clustering-aware Learning of Embeddings for Speaker Diarisation. CoRR Evonne P. C. Lee, Guangzhi Sun, Chao Zhang, Philip C. Woodland
2022	A	`conf`	Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription. INTERSPEECH Xianrui Zheng, Chao Zhang, Philip C. Woodland
2022	J	`jnl`	Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription. CoRR Xianrui Zheng, Chao Zhang, Philip C. Woodland
2022	A	`conf`	Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition. INTERSPEECH Guangzhi Sun, Chao Zhang, Philip C. Woodland
2022	J	`jnl`	Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training. CoRR Adnan Haider, Chao Zhang, Florian L. Kreyssig, Philip C. Woodland
2021	J	`jnl`	A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training. Neural Networks Adnan Haider, Chao Zhang, Florian L. Kreyssig, Philip C. Woodland
2021	C	`conf`	Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition. ASRU Xianrui Zheng, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition. CoRR Xianrui Zheng, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	Combination of deep speaker embeddings for diarisation. Neural Networks Guangzhi Sun, Chao Zhang, Philip C. Woodland
2021	Misc	`conf`	Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition. ICASSP Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman
2021	Misc	`conf`	Content-Aware Speaker Embeddings for Speaker Diarisation. ICASSP Guangzhi Sun, D. Liu, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	Content-Aware Speaker Embeddings for Speaker Diarisation. CoRR Guangzhi Sun, D. Liu, Chao Zhang, Philip C. Woodland
2021	—	`conf`	Discriminative Neural Clustering for Speaker Diarisation. SLT Qiujia Li, Florian L. Kreyssig, Chao Zhang, Philip C. Woodland
2021	Misc	`conf`	Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations. ICASSP Wen Wu, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition. CoRR Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland
2021	A	`conf`	Residual Energy-Based Models for End-to-End Speech Recognition. Interspeech Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland
2021	J	`jnl`	Residual Energy-Based Models for End-to-End Speech Recognition. CoRR Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland
2021	Misc	`conf`	Transformer Language Models with LSTM-Based Cross-Utterance Information Representation. ICASSP Guangzhi Sun, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	Transformer Language Models with LSTM-based Cross-utterance Information Representation. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2021	C	`conf`	Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition. ASRU Guangzhi Sun, Chao Zhang, Philip C. Woodland
2021	J	`jnl`	Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2021	A	`conf`	Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning. Interspeech Dongcheng Jiang, Chao Zhang, Philip C. Woodland
2020	J	`jnl`	Combination of Deep Speaker Embeddings for Diarisation. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2020	J	`jnl`	Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition. CoRR Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman
2020	A	`conf`	Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings. INTERSPEECH Florian L. Kreyssig, Philip C. Woodland
2020	J	`jnl`	Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings. CoRR Florian L. Kreyssig, Philip C. Woodland
2020	J	`jnl`	Cross-Utterance Language Models with Acoustic Error Sampling. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2020	J	`jnl`	Emotion recognition by fusing time synchronous and time asynchronous representations. CoRR Wen Wu, Chao Zhang, Philip C. Woodland
2020	Misc	`conf`	Improved Large-Margin Softmax Loss for Speaker Diarisation. ICASSP Yassir Fathullah, Chao Zhang, Philip C. Woodland
2019	J	`jnl`	Discriminative Neural Clustering for Speaker Diarisation. CoRR Qiujia Li, Florian L. Kreyssig, Chao Zhang, Philip C. Woodland
2019	J	`jnl`	Improved Large-margin Softmax Loss for Speaker Diarisation. CoRR Yassir Fathullah, Chao Zhang, Philip C. Woodland
2019	C	`conf`	Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition. ASRU Qiujia Li, Chao Zhang, Philip C. Woodland
2019	J	`jnl`	Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition. CoRR Qiujia Li, Chao Zhang, Philip C. Woodland
2019	A	`conf`	Multi-Span Acoustic Modelling Using Raw Waveform Signals. INTERSPEECH Patrick von Platen, Chao Zhang, Philip C. Woodland
2019	J	`jnl`	Multi-Span Acoustic Modelling using Raw Waveform Signals. CoRR Patrick von Platen, Chao Zhang, Philip C. Woodland
2019	Misc	`conf`	PyHTK: Python Library and ASR Pipelines for HTK. ICASSP Chao Zhang, Florian L. Kreyssig, Qiujia Li, Philip C. Woodland
2019	Misc	`conf`	Speaker Diarisation Using 2D Self-attentive Combination of Embeddings. ICASSP Guangzhi Sun, Chao Zhang, Philip C. Woodland
2019	J	`jnl`	Speaker diarisation using 2D self-attentive combination of embeddings. CoRR Guangzhi Sun, Chao Zhang, Philip C. Woodland
2018	A	`conf`	Combining Natural Gradient with Hessian Free Methods for Sequence Training. INTERSPEECH Adnan Haider, Philip C. Woodland
2018	J	`jnl`	Combining Natural Gradient with Hessian Free Methods for Sequence Training. CoRR Adnan Haider, Philip C. Woodland
2018	Misc	`conf`	High Order Recurrent Neural Networks for Acoustic Modelling. ICASSP Chao Zhang, Philip C. Woodland
2018	J	`jnl`	High Order Recurrent Neural Networks for Acoustic Modelling. CoRR Chao Zhang, Philip C. Woodland
2018	J	`jnl`	Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs. CoRR Florian Kreyssig, Chao Zhang, Philip C. Woodland
2018	Misc	`conf`	Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS. ICASSP Florian L. Kreyssig, Chao Zhang, Philip C. Woodland
2018	A	`conf`	Semi-tied Units for Efficient Gating in LSTM and Highway Networks. INTERSPEECH Chao Zhang, Philip C. Woodland
2018	J	`jnl`	Semi-tied Units for Efficient Gating in LSTM and Highway Networks. CoRR Chao Zhang, Philip C. Woodland
2018	J	`jnl`	Sequence Training of DNN Acoustic Models With Natural Gradient. CoRR Adnan Haider, Philip C. Woodland
2018	A	`conf`	Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems. INTERSPEECH Yu Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland
2017	J	`jnl`	I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models. IEEE ACM Trans. Audio Speech Lang. Process. Penny Karanasou, Chunyang Wu, Mark J. F. Gales, Philip C. Woodland
2017	Misc	`conf`	Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training. ICASSP Chao Zhang, Philip C. Woodland
2017	J	`jnl`	Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem. PLoS Comput. Biol. Cai Wingfield, Li Su, Xunying Liu, Chao Zhang, Philip C. Woodland, Andrew Thwaites, Elisabeth Fonteneau, William D. Marslen-Wilson
2017	C	`conf`	Sequence training of DNN acoustic models with natural gradient. ASRU Adnan Haider, Philip C. Woodland
2016	Misc	`conf`	CUED-RNNLM - An open-source toolkit for efficient training and evaluation of recurrent neural network language models. ICASSP Xie Chen, Xunying Liu, Y. Qian, Mark J. F. Gales, Philip C. Woodland
2016	Misc	`conf`	DNN speaker adaptation using parameterised sigmoid and ReLU hidden activation functions. ICASSP Chao Zhang, Philip C. Woodland
2016	J	`jnl`	Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. Xie Chen, Xunying Liu, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland
2016	Misc	`conf`	Improved DNN-based segmentation for multi-genre broadcast audio. ICASSP Linlin Wang, Chao Zhang, Philip C. Woodland, Mark J. F. Gales, Panagiota Karanasou, Pierre Lanchantin, Xunying Liu, Yanmin Qian
2016	A	`conf`	Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems. INTERSPEECH Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanman Qian, Linlin Wang, Philip C. Woodland, Chao Zhang
2016	Misc	`conf`	System combination with log-linear models. ICASSP J. Yang, Chao Zhang, Anton Ragni, Mark J. F. Gales, Philip C. Woodland
2016	J	`jnl`	Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models. IEEE ACM Trans. Audio Speech Lang. Process. Xunying Liu, Xie Chen, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland
2016	J	`jnl`	Very Deep Convolutional Neural Networks for Robust Speech Recognition. CoRR Yanmin Qian, Philip C. Woodland
2016	—	`conf`	Very deep convolutional neural networks for robust speech recognition. SLT Yanmin Qian, Philip C. Woodland
2015	A	`conf`	A general artificial neural network extension for HTK. INTERSPEECH Chao Zhang, Philip C. Woodland
2015	C	`conf`	Cambridge university transcription systems for the multi-genre broadcast challenge. ASRU Philip C. Woodland, Xunying Liu, Yanmin Qian, Chao Zhang, Mark J. F. Gales, Penny Karanasou, Pierre Lanchantin, Linlin Wang
2015	A	`conf`	I-vector estimation using informative priors for adaptation of deep neural networks. INTERSPEECH Penny Karanasou, Mark J. F. Gales, Philip C. Woodland
2015	Misc	`conf`	Improving the training and evaluation efficiency of recurrent neural network language models. ICASSP Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2015	C	`conf`	Investigation of back-off based interpolation between recurrent neural network and n-gram language models. ASRU Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2015	A	`conf`	Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages. INTERSPEECH Haipeng Wang, Anton Ragni, Mark J. F. Gales, Kate M. Knill, Philip C. Woodland, Chao Zhang
2015	C	`conf`	Multilingual representations for low resource speech recognition and keyword search. ASRU Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran, Abhinav Sethy, Kartik Audhkhasi, Xiaodong Cui, Ellen Kislal, Lidia Mangu, Markus Nußbaum-Thom, Michael Picheny, Zoltán Tüske, Pavel Golik, Ralf Schlüter, Hermann Ney, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang, Philip C. Woodland
2015	A	`conf`	Parameterised sigmoid and reLU hidden activation functions for DNN acoustic modelling. INTERSPEECH Chao Zhang, Philip C. Woodland
2015	Misc	`conf`	Paraphrastic recurrent neural network language models. ICASSP Xunying Liu, Xie Chen, Mark J. F. Gales, Philip C. Woodland
2015	A	`conf`	Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. INTERSPEECH Xie Chen, Tian Tan, Xunying Liu, Pierre Lanchantin, M. Wan, Mark J. F. Gales, Philip C. Woodland
2015	Misc	`conf`	Recurrent neural network language model training with noise contrastive estimation for speech recognition. ICASSP Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2015	C	`conf`	Speaker diarisation and longitudinal linking in multi-genre broadcast data. ASRU Penny Karanasou, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang
2015	A	`conf`	The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation. INTERSPEECH Xunying Liu, Federico Flego, Linlin Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland
2015	C	`conf`	The MGB challenge: Evaluating multi-genre broadcast media recognition. ASRU 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	C	`conf`	The development of the cambridge university alignment systems for the multi-genre broadcast challenge. ASRU Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang
2014	A	`conf`	Adaptation of deep neural network acoustic models using factorised i-vectors. INTERSPEECH Penny Karanasou, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland
2014	Misc	`conf`	Detecting deletions in ASR output. ICASSP Matthew Stephen Seigel, Philip C. Woodland
2014	Misc	`conf`	Direct sub-word confidence estimation with hidden-state conditional random fields. ICASSP Matthew Stephen Seigel, Philip C. Woodland
2014	A	`conf`	Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch. INTERSPEECH Xie Chen, Yongqiang Wang, Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2014	Misc	`conf`	Efficient lattice rescoring using recurrent neural network language models. ICASSP Xunying Liu, Yongqiang Wang, Xie Chen, Mark J. F. Gales, Philip C. Woodland
2014	J	`jnl`	Paraphrastic language models. Comput. Speech Lang. Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2014	Misc	`conf`	Paraphrastic neural network language models. ICASSP Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2014	Misc	`conf`	Standalone training of context-dependent deep neural network acoustic models. ICASSP Chao Zhang, Philip C. Woodland
2013	Misc	`conf`	A confidence-based approach for improving keyword hypothesis scores. ICASSP Matthew Stephen Seigel, Philip C. Woodland, Mark J. F. Gales
2013	Misc	`conf`	A high-performance Cantonese keyword search system. ICASSP Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Kate M. Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter, Abhinav Sethy, Philip C. Woodland
2013	—	`conf`	Automatic Transcription of Multi-genre Media Archives. SLAM@INTERSPEECH 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	A	`conf`	Cross-domain paraphrasing for improving language modelling using out-of-domain data. INTERSPEECH Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2013	A	`conf`	Improving lightly supervised training for broadcast transcription. INTERSPEECH Yanhua Long, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Matthew Stephen Seigel, Philip C. Woodland
2013	C	`conf`	Investigation of multilingual deep neural networks for spoken term detection. ASRU Kate M. Knill, Mark J. F. Gales, Shakti P. Rath, Philip C. Woodland, Chao Zhang, Shi-Xiong Zhang
2013	J	`jnl`	Language model cross adaptation for LVCSR system combination. Comput. Speech Lang. Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2013	Misc	`conf`	Paraphrastic language models and combination with neural network language models. ICASSP Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2013	Misc	`conf`	System combination and score normalization for spoken term detection. ICASSP Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Brian Kingsbury, Kate M. Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter, Abhinav Sethy, Philip C. Woodland
2013	J	`jnl`	Use of contexts in language model interpolation and adaptation. Comput. Speech Lang. Xunying Liu, Mark John Francis Gales, Philip C. Woodland
2012	A	`conf`	Complementary Phone Error Training. INTERSPEECH Frank Diehl, Philip C. Woodland
2012	J	`jnl`	Morphological decomposition in Arabic ASR systems. Comput. Speech Lang. Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland
2012	A	`conf`	Paraphrastic Language Models. INTERSPEECH Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2012	—	`conf`	Transcription of multi-genre media archives using out-of-domain data. SLT Peter Bell, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanhua Long, Steve Renals, Pawel Swietojanski, Philip C. Woodland
2012	A	`conf`	Using Sub-word-level Information for Confidence Estimation with Conditional Random Field Models. INTERSPEECH Matthew Stephen Seigel, Philip C. Woodland
2011	A	`conf`	Combining Information Sources for Confidence Estimation with CRF Models. INTERSPEECH Matthew Stephen Seigel, Philip C. Woodland
2011	A	`conf`	Graphone Model Interpolation and Arabic Pronunciation Generation. INTERSPEECH T. Li, Philip C. Woodland, Frank Diehl, Mark J. F. Gales
2011	A	`conf`	Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation. INTERSPEECH Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2011	Misc	`conf`	Investigation of acoustic units for LVCSR systems. ICASSP Xunying Liu, Mark John Francis Gales, Jim L. Hieronymus, Philip C. Woodland
2011	J	`jnl`	The efficient incorporation of MLP features into automatic speech recognition systems. Comput. Speech Lang. Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland
2011	A	`conf`	Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems. INTERSPEECH Frank Diehl, Mark John Francis Gales, Xunying Liu, Marcus Tomalin, Philip C. Woodland
2010	A	`conf`	Improved neural network based language modelling and adaptation. INTERSPEECH Junho Park, Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2010	Misc	`conf`	Language model combination and adaptation usingweighted finite state transducers. ICASSP Xunying Liu, Mark J. F. Gales, Jim L. Hieronymus, Philip C. Woodland
2010	A	`conf`	Language model cross adaptation for LVCSR system combination. INTERSPEECH Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2010	Misc	`conf`	Recent improvements to the Cambridge Arabic Speech-to-Text systems. ICASSP Marcus Tomalin, Frank Diehl, Mark J. F. Gales, Junho Park, Philip C. Woodland
2010	J	`jnl`	Unsupervised training and directed manual transcription for LVCSR. Speech Commun. Kai Yu, Mark J. F. Gales, Lan Wang, Philip C. Woodland
2009	A	`conf`	Efficient generation and use of MLP features for Arabic speech recognition. INTERSPEECH Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland
2009	A	`conf`	Exploiting Chinese character models to improve speech recognition performance. INTERSPEECH Jim L. Hieronymus, Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2009	A	`conf`	Morphological analysis and decomposition for Arabic speech-to-text systems. INTERSPEECH Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland
2009	Misc	`conf`	Training and adapting MLP features for Arabic speech recognition. ICASSP Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland
2009	J	`jnl`	Unsupervised Adaptation With Discriminative Mapping Transforms. IEEE Trans. Speech Audio Process. Kai Yu, Mark J. F. Gales, Philip C. Woodland
2009	A	`conf`	Use of contexts in language model interpolation and adaptation. INTERSPEECH Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2008	A	`conf`	Context dependent language model adaptation. INTERSPEECH Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2008	J	`jnl`	MPE-based discriminative linear transforms for speaker adaptation. Comput. Speech Lang. Lan Wang, Philip C. Woodland
2008	Misc	`conf`	Phonetic pronunciations for arabic speech-to-text systems. ICASSP Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland
2008	Misc	`conf`	Unsupervised discriminative adaptation using discriminative mapping transforms. ICASSP Kai Yu, Mark J. F. Gales, Philip C. Woodland
2007	—	`conf`	Consensus Network Decoding for Statistical Machine Translation System Combination. ICASSP (4) Khe Chai Sim, William J. Byrne, Mark J. F. Gales, Hichem Sahbi, Philip C. Woodland
2007	C	`conf`	Development of a phonetic system for large vocabulary Arabic speech recognition. ASRU Mark J. F. Gales, Frank Diehl, Chandra Kant Raut, Marcus Tomalin, Philip C. Woodland, Kai Yu
2007	C	`conf`	Discriminative language model adaptation for Mandarin broadcast speech transcription and translation. ASRU Xunying Liu, William J. Byrne, Mark J. F. Gales, Adrià de Gispert, Marcus Tomalin, Philip C. Woodland, Kai Yu
2007	—	`conf`	Improving Speech Transcription for Mandarin-English Translation. ICASSP (4) Marcus Tomalin, Mark J. F. Gales, X. Andrew Liu, Khe Chai Sim, Rohit Sinha, Lan Wang, Philip C. Woodland, Kai Yu
2007	—	`conf`	Speech Recognition System Combination for Machine Translation. ICASSP (4) 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	—	`conf`	Unsupervised Training for Mandarin Broadcast News and Conversation Transcription. ICASSP (4) Lan Wang, Mark J. F. Gales, Philip C. Woodland
2007	A	`conf`	Unsupervised training with directed manual transcription for recognising Mandarin broadcast audio. INTERSPEECH Kai Yu, Mark J. F. Gales, Philip C. Woodland
2006	J	`jnl`	Corrections to "Automatic Transcription of Conversational Telephone Speech". IEEE Trans. Speech Audio Process. Thomas Hain, Philip C. Woodland, Gunnar Evermann, Mark J. F. Gales, Xunying Liu, Gareth L. Moore, Daniel Povey, Lan Wang
2006	—	`conf`	Discriminatively Trained Gaussian Mixture Models for Sentence Boundary Detection. ICASSP (1) Marcus Tomalin, Philip C. Woodland
2006	J	`jnl`	Progress in the CU-HTK broadcast news transcription system. IEEE Trans. Speech Audio Process. Mark J. F. Gales, Do Yeong Kim, Philip C. Woodland, Ho Yin Chan, David Mrva, Rohit Sinha, S. E. Tranter
2006	—	`conf`	The Cu-Htk Mandarin Broadcast News Transcription System. ICASSP (1) Rohit Sinha, Mark J. F. Gales, Do Yeong Kim, X. Andrew Liu, Khe Chai Sim, Philip C. Woodland
2006	A	`conf`	Unsupervised language model adaptation for Mandarin broadcast conversation transcription. INTERSPEECH David Mrva, Philip C. Woodland
2005	J	`jnl`	Automatic transcription of conversational telephone speech. IEEE Trans. Speech Audio Process. Thomas Hain, Philip C. Woodland, Gunnar Evermann, Mark J. F. Gales, Xunying Liu, Gareth L. Moore, Daniel Povey, Lan Wang
2005	—	`conf`	Development of the CU-HTK 2004 Broadcast News Transcription Systems. ICASSP (1) Do Yeong Kim, Ho Yin Chan, Gunnar Evermann, Mark J. F. Gales, David Mrva, Khe Chai Sim, Philip C. Woodland
2005	—	`conf`	Development of the CUHTK 2004 Mandarin Conversational Telephone Speech Transcription System. ICASSP (1) Mark J. F. Gales, Bin Jia, X. Andrew Liu, Khe Chai Sim, Philip C. Woodland, Kai Yu
2005	—	`conf`	Structural metadata research in the EARS program. ICASSP (5) Yang Liu, Elizabeth Shriberg, Andreas Stolcke, Barbara Peskin, Jeremy Ang, Dustin Hillard, Mari Ostendorf, Marcus Tomalin, Philip C. Woodland, Mary P. Harper
2005	A	`conf`	The Cambridge University March 2005 speaker diarisation system. INTERSPEECH Rohit Sinha, S. E. Tranter, Mark J. F. Gales, Philip C. Woodland
2005	—	`conf`	Training LVCSR Systems on Thousands of Hours of Data. ICASSP (1) Gunnar Evermann, Ho Yin Chan, Mark J. F. Gales, Bin Jia, David Mrva, Philip C. Woodland, Kai Yu
2004	A	`conf`	A PLSA-based language model for conversational telephone speech. INTERSPEECH David Mrva, Philip C. Woodland
2004	J	`jnl`	Automatic capitalisation generation for speech input. Comput. Speech Lang. Ji-Hwan Kim, Philip C. Woodland
2004	—	`conf`	Development of the 2003 CU-HTK conversational telephone speech transcription system. ICASSP (1) Gunnar Evermann, Ho Yin Chan, Mark J. F. Gales, Thomas Hain, Xunying Liu, David Mrva, Lan Wang, Philip C. Woodland
2004	—	`conf`	Generating and evaluating segmentations for automatic speech recognition of conversational telephone speech. ICASSP (1) Sue Tranter, Kai Yu, Gunnar Evermann, Philip C. Woodland
2004	—	`conf`	Improving broadcast news transcription by lightly supervised discriminative training. ICASSP (1) Ho Yin Chan, Philip C. Woodland
2004	—	`conf`	MPE-based discriminative linear transform for speaker adaptation. ICASSP (1) Lan Wang, Philip C. Woodland
2004	A	`conf`	Using VTLN for broadcast news transcription. INTERSPEECH Do Yeong Kim, Srinivasan Umesh, Mark J. F. Gales, Thomas Hain, Philip C. Woodland
2003	J	`jnl`	A combined punctuation generation and speech recognition system and its performance enhancement using prosody. Speech Commun. Ji-Hwan Kim, Philip C. Woodland
2003	—	`conf`	Automatic complexity control for HLDA systems. ICASSP (1) Xunying Liu, Mark J. F. Gales, Philip C. Woodland
2003	—	`conf`	Discriminative map for acoustic model adaptation. ICASSP (1) Daniel Povey, Philip C. Woodland, Mark J. F. Gales
2003	J	`jnl`	Erratum: Language modelling for Russian and English using words and classes [Computer Speech and Language 17 (2003) 87-104]. Comput. Speech Lang. Edward W. D. Whittaker, Philip C. Woodland
2003	J	`jnl`	Language modelling for Russian and English using words and classes. Comput. Speech Lang. Edward W. D. Whittaker, Philip C. Woodland
2003	A	`conf`	MMI-MAP and MPE-MAP for acoustic model adaptation. INTERSPEECH Daniel Povey, Mark J. F. Gales, Do Yeong Kim, Philip C. Woodland
2003	—	`conf`	Porting: SwitchBoard to the VoiceMail task. ICASSP (1) Mark J. F. Gales, Yuan Dong, Daniel Povey, Philip C. Woodland
2002	A	`conf`	Cluster identification for speaker-environment tracking. INTERSPEECH J. T. Wickramaratna, Philip C. Woodland
2002	Misc	`conf`	Implementation of automatic capitalisation generation systems for speech input. ICASSP Ji-Hwan Kim, Philip C. Woodland
2002	Misc	`conf`	Improved cross-task recognition using MMIE training. ICASSP Ricardo de Córdoba, Philip C. Woodland, Mark J. F. Gales
2002	J	`jnl`	Large scale discriminative training of hidden Markov models for speech recognition. Comput. Speech Lang. Philip C. Woodland, Daniel Povey
2002	A	`conf`	Maximum mutual information training of hidden Markov models with vector linear predictors. INTERSPEECH K. K. Chin, Philip C. Woodland
2002	Misc	`conf`	Minimum Phone Error and I-smoothing for improved discriminative training. ICASSP Daniel Povey, Philip C. Woodland
2002	J	`jnl`	The development of the HTK Broadcast News transcription system: An overview. Speech Commun. Philip C. Woodland
2001	Misc	`conf`	Efficient class-based language modelling for very large vocabularies. ICASSP Edward W. D. Whittaker, Philip C. Woodland
2001	Misc	`conf`	Improved discriminative training techniques for large vocabulary continuous speech recognition. ICASSP Daniel Povey, Philip C. Woodland
2001	Misc	`conf`	Improvements in linear transform based speaker adaptation. ICASSP Luís Felipe Uebel, Philip C. Woodland
2001	J	`jnl`	Information Retrieval from Unsegmented Broadcast News Audio. Int. J. Speech Technol. Sue E. Johnson, Pierre Jourlin, Karen Spärck Jones, Philip C. Woodland
2001	Misc	`conf`	New features in the CU-HTK system for transcription of conversational telephone speech. ICASSP Thomas Hain, Philip C. Woodland, Gunnar Evermann, Daniel Povey
2001	J	`jnl`	The Cambridge University Multimedia Document Retrieval Demo System. Int. J. Speech Technol. Andreas Tuerk, Sue E. Johnson, Pierre Jourlin, Karen Spärck Jones, Philip C. Woodland
2001	A	`conf`	The use of prosody in a combined system for punctuation generation and speech recognition. INTERSPEECH Ji-Hwan Kim, Philip C. Woodland
2000	Misc	`conf`	A method for direct audio search with applications to indexing and retrieval. ICASSP Sue E. Johnson, Philip C. Woodland
2000	A	`conf`	A rule-based named entity recognition system for speech input. INTERSPEECH Ji-Hwan Kim, Philip C. Woodland
2000	—	`conf`	Audio Indexing and Retrieval of Complete Broadcoast News Shows. RIAO Sue E. Johnson, Pierre Jourlin, Karen Sparck Jones, Philip C. Woodland
2000	A*	`conf`	Effects of out of vocabulary words in spoken document retrieval. SIGIR Philip C. Woodland, Sue E. Johnson, Pierre Jourlin, Karen Sparck Jones
2000	Misc	`conf`	Large vocabulary decoding and confidence estimation using word posterior probabilities. ICASSP Gunnar Evermann, Philip C. Woodland
2000	A	`conf`	Modelling sub-phone insertions and deletions in continuous speech recognition. INTERSPEECH Thomas Hain, Philip C. Woodland
2000	A	`conf`	Particle-based language modelling. INTERSPEECH Edward W. D. Whittaker, Philip C. Woodland
2000	—	`conf`	Spoken Document Retrieval for TREC-9 at Cambridge University. TREC Sue E. Johnson, Pierre Jourlin, Karen Sparck Jones, Philip C. Woodland
2000	J	`jnl`	Spoken document representations for probabilistic retrieval. Speech Commun. Pierre Jourlin, Sue E. Johnson, Karen Spärck Jones, Philip C. Woodland
2000	A*	`conf`	The Cambridge University multimedia document retrieval demo system. SIGIR Andreas Tuerk, Sue E. Johnson, Pierre Jourlin, Karen Sparck Jones, Philip C. Woodland
1999	J	`jnl`	A hidden Markov-model-based trainable speech synthesizer. Comput. Speech Lang. Robert E. Donovan, Philip C. Woodland
1999	—	`conf`	An investigation into vocal tract length normalisation. EUROSPEECH Luís Felipe Uebel, Philip C. Woodland
1999	—	`conf`	Dynamic HMM selection for continuous speech recognition. EUROSPEECH Thomas Hain, Philip C. Woodland
1999	Misc	`conf`	Frame discrimination training for HMMs for large vocabulary speech recognition. ICASSP Daniel Povey, Philip C. Woodland
1999	—	`conf`	Improvements in accuracy and speed in the HTK broadcast news transcription system. EUROSPEECH Philip C. Woodland, J. J. Odell, Thomas Hain, Gareth L. Moore, Thomas Niesler, Andreas Tuerk, Edward W. D. Whittaker
1999	A*	`conf`	Improving Retrieval on Imperfect Speech Transcriptions (poster abstract). SIGIR Pierre Jourlin, Sue E. Johnson, Karen Sparck Jones, Philip C. Woodland
1999	—	`conf`	Spoken Document Retrieval for TREC-8 at Cambridge University. TREC Sue E. Johnson, Philip C. Woodland, Karen Sparck Jones, Pierre Jourlin
1999	Misc	`conf`	The 1998 HTK system for transcription of conversational telephone speech. ICASSP Thomas Hain, Philip C. Woodland, Thomas Niesler, Edward W. D. Whittaker
1999	Misc	`conf`	The Cambridge University spoken document retrieval system. ICASSP Sue E. Johnson, Pierre Jourlin, Gareth L. Moore, Karen Spärck Jones, Philip C. Woodland
1999	J	`jnl`	Variable-length categoryn-gram language models. Comput. Speech Lang. Thomas Niesler, Philip C. Woodland
1998	—	`conf`	Comparison of language modelling techniques for Russian and English. ICSLP Edward W. D. Whittaker, Philip C. Woodland
1998	Misc	`conf`	Comparison of part-of-speech and automatically derived category-based language models for speech recognition. ICASSP Thomas Niesler, Edward W. D. Whittaker, Philip C. Woodland
1998	Misc	`conf`	Experiments in broadcast news transcription. ICASSP Philip C. Woodland, Thomas Hain, Sue E. Johnson, Thomas Niesler, Andreas Tuerk, Steve J. Young
1998	—	`conf`	Segmentation and classification of broadcast news audio. ICSLP Thomas Hain, Philip C. Woodland
1998	—	`conf`	Speaker clustering using direct maximisation of the MLLR-adapted likelihood. ICSLP Sue E. Johnson, Philip C. Woodland
1998	—	`conf`	Spoken Document Retrieval For TREC-7 At Cambridge University. TREC Sue E. Johnson, Pierre Jourlin, Gareth L. Moore, Karen Sparck Jones, Philip C. Woodland
1998	Misc	`conf`	The use of accent-specific pronunciation dictionaries in acoustic model training. ICASSP Jason J. Humphries, Philip C. Woodland
1997	Misc	`conf`	Broadcast news transcription using HTK. ICASSP Philip C. Woodland, Mark J. F. Gales, David Pye, Steve J. Young
1997	J	`jnl`	Combined Bayesian and predictive techniques for rapid speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. S. M. Ahadi, Philip C. Woodland
1997	Misc	`conf`	Experiments in speaker normalisation and adaptation for large vocabulary speech recognition. ICASSP David Pye, Philip C. Woodland
1997	J	`jnl`	MMIE training of large vocabulary recognition systems. Speech Commun. V. Valtchev, J. J. Odell, Philip C. Woodland, Steve J. Young
1997	Misc	`conf`	Modelling word-pair relations in a category-based language model. ICASSP Thomas Niesler, Philip C. Woodland
1997	J	`jnl`	Multilingual large vocabulary speech recognition: the European SQALE project. Comput. Speech Lang. Steve J. Young, Martine Adda-Decker, Xavier L. Aubert, Christian Dugast, Jean-Luc Gauvain, Dan J. Kershaw, Lori Lamel, David A. van Leeuwen, David Pye, Anthony J. Robinson, Herman J. M. Steeneken, Philip C. Woodland
1997	—	`conf`	Using accent-specific pronunciation modelling for improved large vocabulary continuous speech recognition. EUROSPEECH Jason J. Humphries, Philip C. Woodland
1996	Misc	`conf`	A variable-length category-based n-gram language model. ICASSP Thomas Niesler, Philip C. Woodland
1996	—	`conf`	Combination of word-based and category-based language models. ICSLP Thomas Niesler, Philip C. Woodland
1996	—	`conf`	Discriminative optimisation of large vocabulary recognition systems. ICSLP V. Valtchev, Philip C. Woodland, Steve J. Young
1996	Misc	`conf`	Improving environmental robustness in large vocabulary speech recognition. ICASSP Philip C. Woodland, Mark John Francis Gales, David Pye
1996	—	`conf`	Iterative unsupervised adaptation using maximum likelihood linear regression. ICSLP Philip C. Woodland, David Pye, Mark J. F. Gales
1996	Misc	`conf`	Lattice-based discriminative training for large vocabulary speech recognition. ICASSP Valtcho Valtchev, Julian Odell, Philip C. Woodland, Steve J. Young
1996	J	`jnl`	Mean and variance adaptation within the MLLR framework. Comput. Speech Lang. Mark J. F. Gales, Philip C. Woodland
1996	—	`conf`	Using accent-specific pronunciation modelling for robust speech recognition. ICSLP Jason J. Humphries, Philip C. Woodland, David J. B. Pearce
1996	—	`conf`	Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation. ICSLP Mark J. F. Gales, David Pye, Philip C. Woodland
1995	Misc	`conf`	Automatic speech synthesiser parameter estimation using HMMs. ICASSP Robert E. Donovan, Philip C. Woodland
1995	—	`conf`	Flexible speaker adaptation for large vocabulary speech recognition. EUROSPEECH C. J. Leggetter, Philip C. Woodland
1995	—	`conf`	Improvements in an HMM-based speech synthesiser. EUROSPEECH Robert E. Donovan, Philip C. Woodland
1995	—	`conf`	Large vocabulary multilingual speech recognition using HTK. EUROSPEECH David Pye, Philip C. Woodland, Steve J. Young
1995	J	`jnl`	Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. C. J. Leggetter, Philip C. Woodland
1995	Misc	`conf`	Rapid speaker adaptation using model prediction. ICASSP S. M. Ahadi, Philip C. Woodland
1995	Misc	`conf`	The 1994 HTK large vocabulary speech recognition system. ICASSP Philip C. Woodland, C. J. Leggetter, Julian Odell, Valtcho Valtchev, Steve J. Young
1994	—	`conf`	A One Pass Decoder Design For Large Vocabulary Recognition. HLT J. J. Odell, V. Valtchev, Philip C. Woodland, Steve J. Young
1994	—	`conf`	Large vocabulary continuous speech recognition using HTK. ICASSP (2) Philip C. Woodland, J. J. Odell, V. Valtchev, Steve J. Young
1994	—	`conf`	Modelling syllable characteristics to improve a large vocabulary continuous speech recogniser. ICSLP M. Jones, Philip C. Woodland
1994	—	`conf`	Recognition ********* a dynamic network decoder design for large vocabulary speech recognition. ICSLP V. Valtchev, J. J. Odell, Philip C. Woodland, Steve J. Young
1994	—	`conf`	Speaker adaptation of continuous density HMMs using multivariate linear regression. ICSLP C. J. Leggetter, Philip C. Woodland
1994	J	`jnl`	Spontaneous speech recognition for the credit card corpus using the HTK toolkit. IEEE Trans. Speech Audio Process. Steve J. Young, Philip C. Woodland, William J. Byrne
1994	J	`jnl`	State clustering in hidden Markov model-based continuous speech recognition. Comput. Speech Lang. Steve J. Young, Philip C. Woodland
1994	—	`conf`	Tree-Based State Tying for High Accuracy Modelling. HLT Steve J. Young, J. J. Odell, Philip C. Woodland
1993	—	`conf`	A wave digital filter model of the entire auditory periphery. ICASSP (2) Christian Giguère, Philip C. Woodland
1993	—	`conf`	Exploiting variable-width features in large vocabulary speech recognition. ICASSP (2) M. Jones, Philip C. Woodland
1993	—	`conf`	Hidden Markov models using shared vector linear predictors. EUROSPEECH B. A. Maxwell, Philip C. Woodland
1993	—	`conf`	The HTK tied-state continuous speech recogniser. EUROSPEECH Philip C. Woodland, Steve J. Young
1993	—	`conf`	The use of state tying in continuous speech recognition. EUROSPEECH Steve J. Young, Philip C. Woodland
1993	—	`conf`	Using relative duration in large vocabulary speech recognition. EUROSPEECH M. Jones, Philip C. Woodland
1992	Misc	`conf`	Hidden Markov models using vector linear prediction and discriminative output distributions. ICASSP Philip C. Woodland
1991	Misc	`conf`	Optimising hidden Markov models using discriminative output distributions. ICASSP Philip C. Woodland, David R. Cole
1990	J	`jnl`	An experimental comparison of connectionist and conventional classification systems on natural data. Speech Commun. Philip C. Woodland, S. G. Smyth