


Остановите войну!
for scientists:
Philip C. Woodland
Person information

Refine list

refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2022
- [c172]Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland:
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition. ICASSP 2022: 6537-6541 - [c171]Xiaoyu Yang, Qiujia Li, Philip C. Woodland:
Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-Trained Models. ICASSP 2022: 8527-8531 - [i25]Wen Wu, Chao Zhang, Xixin Wu, Philip C. Woodland:
Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors. CoRR abs/2203.04443 (2022) - [i24]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator. CoRR abs/2205.09058 (2022) - 2021
- [j36]Guangzhi Sun, Chao Zhang
, Philip C. Woodland:
Combination of deep speaker embeddings for diarisation. Neural Networks 141: 372-384 (2021) - [j35]Adnan Haider
, Chao Zhang
, Florian L. Kreyssig
, Philip C. Woodland:
A distributed optimisation framework combining natural gradient with Hessian-free for discriminative sequence training. Neural Networks 143: 537-549 (2021) - [c170]Xianrui Zheng, Chao Zhang, Philip C. Woodland:
Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition. ASRU 2021: 162-168 - [c169]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Tree-Constrained Pointer Generator for End-to-End Contextual Speech Recognition. ASRU 2021: 780-787 - [c168]Wen Wu, Chao Zhang, Philip C. Woodland:
Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations. ICASSP 2021: 6269-6273 - [c167]Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman:
Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition. ICASSP 2021: 6388-6392 - [c166]Guangzhi Sun, D. Liu, Chao Zhang, Philip C. Woodland:
Content-Aware Speaker Embeddings for Speaker Diarisation. ICASSP 2021: 7168-7172 - [c165]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Transformer Language Models with LSTM-Based Cross-Utterance Information Representation. ICASSP 2021: 7363-7367 - [c164]Dongcheng Jiang, Chao Zhang, Philip C. Woodland:
Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning. Interspeech 2021: 2601-2605 - [c163]Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland:
Residual Energy-Based Models for End-to-End Speech Recognition. Interspeech 2021: 4069-4073 - [c162]Qiujia Li, Florian L. Kreyssig, Chao Zhang, Philip C. Woodland:
Discriminative Neural Clustering for Speaker Diarisation. SLT 2021: 574-581 - [i23]Guangzhi Sun, D. Liu, Chao Zhang, Philip C. Woodland:
Content-Aware Speaker Embeddings for Speaker Diarisation. CoRR abs/2102.06467 (2021) - [i22]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Transformer Language Models with LSTM-based Cross-utterance Information Representation. CoRR abs/2102.06474 (2021) - [i21]Adnan Haider, Chao Zhang, Florian L. Kreyssig, Philip C. Woodland:
A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training. CoRR abs/2103.07554 (2021) - [i20]Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland:
Residual Energy-Based Models for End-to-End Speech Recognition. CoRR abs/2103.14152 (2021) - [i19]Xianrui Zheng, Chao Zhang, Philip C. Woodland:
Adapting GPT, GPT-2 and BERT Language Models for Speech Recognition. CoRR abs/2108.07789 (2021) - [i18]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognition. CoRR abs/2109.00627 (2021) - [i17]Qiujia Li, Yu Zhang, David Qiu, Yanzhang He, Liangliang Cao, Philip C. Woodland:
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition. CoRR abs/2110.03327 (2021) - 2020
- [c161]Yassir Fathullah, Chao Zhang, Philip C. Woodland:
Improved Large-Margin Softmax Loss for Speaker Diarisation. ICASSP 2020: 7104-7108 - [c160]Florian L. Kreyssig, Philip C. Woodland:
Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings. INTERSPEECH 2020: 3241-3245 - [i16]Florian L. Kreyssig, Philip C. Woodland:
Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings. CoRR abs/2008.03756 (2020) - [i15]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Cross-Utterance Language Models with Acoustic Error Sampling. CoRR abs/2009.01008 (2020) - [i14]Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman:
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition. CoRR abs/2010.11428 (2020) - [i13]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Combination of Deep Speaker Embeddings for Diarisation. CoRR abs/2010.12025 (2020) - [i12]Wen Wu, Chao Zhang, Philip C. Woodland:
Emotion recognition by fusing time synchronous and time asynchronous representations. CoRR abs/2010.14102 (2020)
2010 – 2019
- 2019
- [c159]Qiujia Li, Chao Zhang, Philip C. Woodland:
Integrating Source-Channel and Attention-Based Sequence-to-Sequence Models for Speech Recognition. ASRU 2019: 39-46 - [c158]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Speaker Diarisation Using 2D Self-attentive Combination of Embeddings. ICASSP 2019: 5801-5805 - [c157]Chao Zhang, Florian L. Kreyssig, Qiujia Li, Philip C. Woodland:
PyHTK: Python Library and ASR Pipelines for HTK. ICASSP 2019: 6470-6474 - [c156]Patrick von Platen, Chao Zhang, Philip C. Woodland:
Multi-Span Acoustic Modelling Using Raw Waveform Signals. INTERSPEECH 2019: 1393-1397 - [i11]Guangzhi Sun, Chao Zhang, Philip C. Woodland:
Speaker diarisation using 2D self-attentive combination of embeddings. CoRR abs/1902.03190 (2019) - [i10]Patrick von Platen, Chao Zhang, Philip C. Woodland:
Multi-Span Acoustic Modelling using Raw Waveform Signals. CoRR abs/1906.11047 (2019) - [i9]Qiujia Li, Chao Zhang, Philip C. Woodland:
Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition. CoRR abs/1909.06614 (2019) - [i8]Qiujia Li, Florian L. Kreyssig, Chao Zhang, Philip C. Woodland:
Discriminative Neural Clustering for Speaker Diarisation. CoRR abs/1910.09703 (2019) - [i7]Yassir Fathullah, Chao Zhang, Philip C. Woodland:
Improved Large-margin Softmax Loss for Speaker Diarisation. CoRR abs/1911.03970 (2019) - 2018
- [c155]Florian L. Kreyssig, Chao Zhang, Philip C. Woodland:
Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS. ICASSP 2018: 4864-4868 - [c154]Chao Zhang, Philip C. Woodland:
High Order Recurrent Neural Networks for Acoustic Modelling. ICASSP 2018: 5849-5853 - [c153]Yu Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland:
Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem Systems. INTERSPEECH 2018: 872-876 - [c152]Chao Zhang, Philip C. Woodland:
Semi-tied Units for Efficient Gating in LSTM and Highway Networks. INTERSPEECH 2018: 1773-1777 - [c151]Adnan Haider, Philip C. Woodland:
Combining Natural Gradient with Hessian Free Methods for Sequence Training. INTERSPEECH 2018: 2918-2922 - [i6]Florian Kreyssig, Chao Zhang, Philip C. Woodland:
Improved TDNNs using Deep Kernels and Frequency Dependent Grid-RNNs. CoRR abs/1802.06412 (2018) - [i5]Chao Zhang, Philip C. Woodland:
High Order Recurrent Neural Networks for Acoustic Modelling. CoRR abs/1802.08314 (2018) - [i4]Adnan Haider, Philip C. Woodland:
Sequence Training of DNN Acoustic Models With Natural Gradient. CoRR abs/1804.02204 (2018) - [i3]Chao Zhang, Philip C. Woodland:
Semi-tied Units for Efficient Gating in LSTM and Highway Networks. CoRR abs/1806.06513 (2018) - [i2]Adnan Haider, Philip C. Woodland:
Combining Natural Gradient with Hessian Free Methods for Sequence Training. CoRR abs/1810.01873 (2018) - 2017
- [j34]Cai Wingfield
, Li Su
, Xunying Liu, Chao Zhang, Philip C. Woodland, Andrew Thwaites
, Elisabeth Fonteneau, William D. Marslen-Wilson:
Relating dynamic brain states to dynamic machine states: Human and machine solutions to the speech recognition problem. PLoS Comput. Biol. 13(9) (2017) - [j33]Penny Karanasou, Chunyang Wu, Mark J. F. Gales, Philip C. Woodland:
I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models. IEEE ACM Trans. Audio Speech Lang. Process. 25(4): 818-828 (2017) - [c150]Adnan Haider, Philip C. Woodland:
Sequence training of DNN acoustic models with natural gradient. ASRU 2017: 178-184 - [c149]Chao Zhang, Philip C. Woodland:
Joint optimisation of tandem systems using Gaussian mixture density neural network discriminative sequence training. ICASSP 2017: 5015-5019 - 2016
- [j32]Xunying Liu
, Xie Chen, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland:
Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language Models. IEEE ACM Trans. Audio Speech Lang. Process. 24(8): 1438-1449 (2016) - [j31]Xie Chen, Xunying Liu, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland:
Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 24(11): 2146-2157 (2016) - [c148]Chao Zhang, Philip C. Woodland:
DNN speaker adaptation using parameterised sigmoid and ReLU hidden activation functions. ICASSP 2016: 5300-5304 - [c147]J. Yang, Chao Zhang, Anton Ragni, Mark J. F. Gales, Philip C. Woodland:
System combination with log-linear models. ICASSP 2016: 5675-5679 - [c146]Linlin Wang, Chao Zhang, Philip C. Woodland, Mark J. F. Gales, Panagiota Karanasou, Pierre Lanchantin, Xunying Liu, Yanmin Qian:
Improved DNN-based segmentation for multi-genre broadcast audio. ICASSP 2016: 5700-5704 - [c145]X. Chen, X. Liu, Y. Qian, Mark J. F. Gales, Philip C. Woodland:
CUED-RNNLM - An open-source toolkit for efficient training and evaluation of recurrent neural network language models. ICASSP 2016: 6000-6004 - [c144]Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanman Qian, Linlin Wang, Philip C. Woodland, Chao Zhang:
Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition Systems. INTERSPEECH 2016: 3057-3061 - [c143]Yanmin Qian, Philip C. Woodland:
Very deep convolutional neural networks for robust speech recognition. SLT 2016: 481-488 - [i1]Yanmin Qian, Philip C. Woodland:
Very Deep Convolutional Neural Networks for Robust Speech Recognition. CoRR abs/1610.00277 (2016) - 2015
- [c142]Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Investigation of back-off based interpolation between recurrent neural network and n-gram language models. ASRU 2015: 181-186 - [c141]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:
Multilingual representations for low resource speech recognition and keyword search. ASRU 2015: 259-266 - [c140]Philip C. Woodland, Xunying Liu, Yanmin Qian, Chao Zhang, Mark J. F. Gales, Penny Karanasou, Pierre Lanchantin, Linlin Wang:
Cambridge university transcription systems for the multi-genre broadcast challenge. ASRU 2015: 639-646 - [c139]Pierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang:
The development of the cambridge university alignment systems for the multi-genre broadcast challenge. ASRU 2015: 647-653 - [c138]Penny Karanasou, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang:
Speaker diarisation and longitudinal linking in multi-genre broadcast data. ASRU 2015: 660-666 - [c137]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:
The MGB challenge: Evaluating multi-genre broadcast media recognition. ASRU 2015: 687-693 - [c136]Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Improving the training and evaluation efficiency of recurrent neural network language models. ICASSP 2015: 5401-5405 - [c135]Xunying Liu, Xie Chen, Mark J. F. Gales, Philip C. Woodland:
Paraphrastic recurrent neural network language models. ICASSP 2015: 5406-5410 - [c134]Xie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Recurrent neural network language model training with noise contrastive estimation for speech recognition. ICASSP 2015: 5411-5415 - [c133]Penny Karanasou, Mark J. F. Gales, Philip C. Woodland:
I-vector estimation using informative priors for adaptation of deep neural networks. INTERSPEECH 2015: 2872-2876 - [c132]Xunying Liu, Federico Flego, Linlin Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland:
The Cambridge University 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translation. INTERSPEECH 2015: 3145-3149 - [c131]Chao Zhang, Philip C. Woodland:
Parameterised sigmoid and reLU hidden activation functions for DNN acoustic modelling. INTERSPEECH 2015: 3224-3228 - [c130]X. Chen, T. Tan, Xunying Liu, Pierre Lanchantin, M. Wan, Mark J. F. Gales, Philip C. Woodland:
Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. INTERSPEECH 2015: 3511-3515 - [c129]Chao Zhang, Philip C. Woodland:
A general artificial neural network extension for HTK. INTERSPEECH 2015: 3581-3585 - [c128]Haipeng Wang, Anton Ragni, Mark J. F. Gales, Kate M. Knill, Philip C. Woodland, Chao Zhang:
Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages. INTERSPEECH 2015: 3660-3664 - 2014
- [j30]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Paraphrastic language models. Comput. Speech Lang. 28(6): 1298-1316 (2014) - [c127]Matthew Stephen Seigel, Philip C. Woodland:
Detecting deletions in ASR output. ICASSP 2014: 2302-2306 - [c126]Matthew Stephen Seigel, Philip C. Woodland:
Direct sub-word confidence estimation with hidden-state conditional random fields. ICASSP 2014: 2307-2311 - [c125]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Paraphrastic neural network language models. ICASSP 2014: 4903-4907 - [c124]Xunying Liu, Yongqiang Wang, Xie Chen, Mark J. F. Gales, Philip C. Woodland:
Efficient lattice rescoring using recurrent neural network language models. ICASSP 2014: 4908-4912 - [c123]Chao Zhang, Philip C. Woodland:
Standalone training of context-dependent deep neural network acoustic models. ICASSP 2014: 5597-5601 - [c122]Xie Chen, Yongqiang Wang, Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch. INTERSPEECH 2014: 641-645 - [c121]Penny Karanasou, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland:
Adaptation of deep neural network acoustic models using factorised i-vectors. INTERSPEECH 2014: 2180-2184 - 2013
- [j29]Xunying Liu, Mark John Francis Gales, Philip C. Woodland:
Use of contexts in language model interpolation and adaptation. Comput. Speech Lang. 27(1): 301-321 (2013) - [j28]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Language model cross adaptation for LVCSR system combination. Comput. Speech Lang. 27(4): 928-942 (2013) - [c120]Kate Knill, Mark J. F. Gales, Shakti P. Rath, Philip C. Woodland, Chao Zhang, Shi-Xiong Zhang:
Investigation of multilingual deep neural networks for spoken term detection. ASRU 2013: 138-143 - [c119]Jonathan Mamou, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Brian Kingsbury, Kate Knill, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter, Abhinav Sethy, Philip C. Woodland:
System combination and score normalization for spoken term detection. ICASSP 2013: 8272-8276 - [c118]Brian Kingsbury, Jia Cui, Xiaodong Cui, Mark J. F. Gales, Kate Knill, Jonathan Mamou, Lidia Mangu, David Nolden, Michael Picheny, Bhuvana Ramabhadran, Ralf Schlüter, Abhinav Sethy, Philip C. Woodland:
A high-performance Cantonese keyword search system. ICASSP 2013: 8277-8281 - [c117]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Paraphrastic language models and combination with neural network language models. ICASSP 2013: 8421-8425 - [c116]Matthew Stephen Seigel, Philip C. Woodland, Mark J. F. Gales:
A confidence-based approach for improving keyword hypothesis scores. ICASSP 2013: 8565-8569 - [c115]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:
Automatic Transcription of Multi-genre Media Archives. SLAM@INTERSPEECH 2013: 26-31 - [c114]Yanhua Long, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Matthew Stephen Seigel, Philip C. Woodland:
Improving lightly supervised training for broadcast transcription. INTERSPEECH 2013: 2187-2191 - [c113]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Cross-domain paraphrasing for improving language modelling using out-of-domain data. INTERSPEECH 2013: 3424-3428 - 2012
- [j27]Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland:
Morphological decomposition in Arabic ASR systems. Comput. Speech Lang. 26(4): 229-243 (2012) - [c112]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Paraphrastic Language Models. INTERSPEECH 2012: 1656-1659 - [c111]Matthew Stephen Seigel, Philip C. Woodland:
Using Sub-word-level Information for Confidence Estimation with Conditional Random Field Models. INTERSPEECH 2012: 2338-2341 - [c110]Frank Diehl, Philip C. Woodland:
Complementary Phone Error Training. INTERSPEECH 2012: 2610-2613 - [c109]Peter Bell, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanhua Long, Steve Renals
, Pawel Swietojanski
, Philip C. Woodland:
Transcription of multi-genre media archives using out-of-domain data. SLT 2012: 324-329 - 2011
- [j26]Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland:
The efficient incorporation of MLP features into automatic speech recognition systems. Comput. Speech Lang. 25(3): 519-534 (2011) - [c108]Xunying Liu, Mark John Francis Gales, Jim L. Hieronymus, Philip C. Woodland:
Investigation of acoustic units for LVCSR systems. ICASSP 2011: 4872-4875 - [c107]Frank Diehl, Mark John Francis Gales, Xunying Liu, Marcus Tomalin, Philip C. Woodland:
Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems. INTERSPEECH 2011: 777-780 - [c106]Matthew Stephen Seigel, Philip C. Woodland:
Combining Information Sources for Confidence Estimation with CRF Models. INTERSPEECH 2011: 905-908 - [c105]T. Li, Philip C. Woodland, Frank Diehl, Mark J. F. Gales:
Graphone Model Interpolation and Arabic Pronunciation Generation. INTERSPEECH 2011: 2309-2312 - [c104]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation. INTERSPEECH 2011: 2857-2860 - 2010
- [j25]Kai Yu, Mark J. F. Gales, Lan Wang, Philip C. Woodland:
Unsupervised training and directed manual transcription for LVCSR. Speech Commun. 52(7-8): 652-663 (2010) - [c103]Marcus Tomalin, Frank Diehl, Mark J. F. Gales, Junho Park, Philip C. Woodland:
Recent improvements to the Cambridge Arabic Speech-to-Text systems. ICASSP 2010: 4382-4385 - [c102]Xunying Liu, Mark J. F. Gales, Jim L. Hieronymus, Philip C. Woodland:
Language model combination and adaptation usingweighted finite state transducers. ICASSP 2010: 5390-5393 - [c101]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Language model cross adaptation for LVCSR system combination. INTERSPEECH 2010: 342-345 - [c100]Junho Park, Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Improved neural network based language modelling and adaptation. INTERSPEECH 2010: 1041-1044
2000 – 2009
- 2009
- [j24]Kai Yu, Mark J. F. Gales, Philip C. Woodland:
Unsupervised Adaptation With Discriminative Mapping Transforms. IEEE Trans. Speech Audio Process. 17(4): 714-723 (2009) - [c99]Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland:
Training and adapting MLP features for Arabic speech recognition. ICASSP 2009: 4461-4464 - [c98]Junho Park, Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland:
Efficient generation and use of MLP features for Arabic speech recognition. INTERSPEECH 2009: 236-239 - [c97]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Use of contexts in language model interpolation and adaptation. INTERSPEECH 2009: 360-363 - [c96]Jim L. Hieronymus, Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Exploiting Chinese character models to improve speech recognition performance. INTERSPEECH 2009: 364-367 - [c95]Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland:
Morphological analysis and decomposition for Arabic speech-to-text systems. INTERSPEECH 2009: 2675-2678 - 2008
- [j23]Lan Wang, Philip C. Woodland:
MPE-based discriminative linear transforms for speaker adaptation. Comput. Speech Lang. 22(3): 256-272 (2008) - [c94]Frank Diehl, Mark J. F. Gales, Marcus Tomalin, Philip C. Woodland:
Phonetic pronunciations for arabic speech-to-text systems. ICASSP 2008: 1573-1576 - [c93]Kai Yu, Mark J. F. Gales, Philip C. Woodland:
Unsupervised discriminative adaptation using discriminative mapping transforms. ICASSP 2008: 4273-4276 - [c92]Xunying Liu, Mark J. F. Gales, Philip C. Woodland:
Context dependent language model adaptation. INTERSPEECH 2008: 837-840 - 2007
- [c91]Mark J. F. Gales, Frank Diehl, Chandra Kant Raut, Marcus Tomalin, Philip C. Woodland, Kai Yu:
Development of a phonetic system for large vocabulary Arabic speech recognition. ASRU 2007: 24-29 - [c90]Xunying Liu, William J. Byrne, Mark J. F. Gales, Adrià de Gispert, Marcus Tomalin, Philip C. Woodland, Kai Yu:
Discriminative language model adaptation for Mandarin broadcast speech transcription and translation. ASRU 2007: 153-158 - [c89]Marcus Tomalin, Mark J. F. Gales, X. Andrew Liu, Khe Chai Sim, Rohit Sinha
, Lan Wang, Philip C. Woodland, Kai Yu:
Improving Speech Transcription for Mandarin-English Translation. ICASSP (4) 2007: 97-100 - [c88]Khe Chai Sim, William J. Byrne, Mark J. F. Gales, Hichem Sahbi, Philip C. Woodland:
Consensus Network Decoding for Statistical Machine Translation System Combination. ICASSP (4) 2007: 105-108 - [c87]