Mark J. F. Gales - researchr alias

researchr

You are not signed in
Sign in
Sign up

Viewing Publication 1 - 100 from 223

2019

2018

Active Memory Networks for Language ModelingOscar Chen, Anton Ragni, Mark J. F. Gales, Xie Chen. interspeech 2018: 3338-3342 [doi]

A Log Domain Pulse Model for Parametric Speech SynthesisGilles Degottex, Pierre Lanchantin, Mark J. F. Gales. taslp, 26(1):57-70, 2018. [doi]

A Spectrally Weighted Mixture of Least Square Error and Wasserstein Discriminator Loss for Generative SPSSGilles Degottex, Mark J. F. Gales. slt 2018: 603-609 [doi]

Hierarchical RNNs for Waveform-Level Speech SynthesisQingyun Dou, Moquan Wan, Gilles Degottex, Zhiyi Ma, Mark J. F. Gales. slt 2018: 618-625 [doi]

Impact of ASR Performance on Free Speaking Language AssessmentKate Knill, Mark J. F. Gales, Konstantinos Kyriakopoulos, Andrey Malinin, Anton Ragni, Yu Wang, Andrew Caines. interspeech 2018: 1641-1645 [doi]

A Deep Learning Approach to Assessing Non-native Pronunciation of English Using Phone DistancesKonstantinos Kyriakopoulos, Kate Knill, Mark J. F. Gales. interspeech 2018: 1626-1630 [doi]

Predictive Uncertainty Estimation via Prior NetworksAndrey Malinin, Mark J. F. Gales. nips 2018: 7047-7058 [doi]

Automatic Speech Recognition System Development in the "Wild"Anton Ragni, Mark J. F. Gales. interspeech 2018: 2217-2221 [doi]

Waveform-Based Speaker Representations for Speech SynthesisMoquan Wan, Gilles Degottex, Mark J. F. Gales. interspeech 2018: 897-901 [doi]

Speaker Adaptation and Adaptive Training for Jointly Optimised Tandem SystemsYu Wang, Chao Zhang, Mark J. F. Gales, Philip C. Woodland. interspeech 2018: 872-876 [doi]

Improving Interpretability and Regularization in Deep LearningChunyang Wu, Mark J. F. Gales, Anton Ragni, Penny Karanasou, Khe Chai Sim. taslp, 26(2):256-265, 2018. [doi]

2017

Investigating Bidirectional Recurrent Neural Network Language Models for Speech RecognitionX. Chen, Anton Ragni, X. Liu, Mark J. F. Gales. interspeech 2017: 269-273 [doi]

Recurrent neural network language models for keyword searchX. Chen, Anton Ragni, J. Vasilakes, X. Liu, Kate Knill, Mark J. F. Gales. icassp 2017: 5775-5779 [doi]

Low-Resource Speech Recognition and Keyword-SpottingMark J. F. Gales, Kate M. Knill, Anton Ragni. specom 2017: 3-19 [doi]

I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic ModelsPenny Karanasou, Chunyang Wu, Mark J. F. Gales, Philip C. Woodland. taslp, 25(4):818-828, 2017. [doi]

Use of Graphemic Lexicons for Spoken Language AssessmentKate M. Knill, Mark J. F. Gales, K. Kyriakopoulos, Anton Ragni, Yu Wang. interspeech 2017: 2774-2778 [doi]

Automatic Characterisation of the Pronunciation of Non-native English Speakers using Phone Distance FeaturesKonstantinos Kyriakopoulos, Mark J. F. Gales, Kate Knill. slte 2017: 59-64 [doi]

A hierarchical attention based model for off-topic spontaneous spoken response detectionAndrey Malinin, Kate Knill, Mark J. F. Gales. asru 2017: 397-403 [doi]

Incorporating Uncertainty into Deep Learning for Spoken Language AssessmentAndrey Malinin, Anton Ragni, Kate Knill, Mark J. F. Gales. acl 2017: 45-50 [doi]

An attention based model for off-topic spontaneous spoken response detection: An Initial StudyAndrey Malinin, Kate Knill, Anton Ragni, Yu Wang, Mark J. F. Gales. slte 2017: 144-149 [doi]

Stimulated training for automatic speech recognition and keyword search in limited resource conditionsAnton Ragni, C. Wu, Mark J. F. Gales, J. Vasilakes, Kate M. Knill. icassp 2017: 4830-4834 [doi]

Integrated speaker-adaptive speech synthesisMoquan Wan, Gilles Degottex, Mark J. F. Gales. asru 2017: 705-711 [doi]

Multi-task ensembles with teacher-student trainingJeremy H. M. Wong, Mark J. F. Gales. asru 2017: 84-90 [doi]

Student-Teacher Training with Diverse Decision Tree EnsemblesJeremy H. M. Wong, Mark J. F. Gales. interspeech 2017: 117-121 [doi]

Deep Activation Mixture Model for Speech RecognitionChunyang Wu, Mark J. F. Gales. interspeech 2017: 1611-1615 [doi]

2016

Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech RecognitionXie Chen, Xunying Liu, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland. taslp, 24(11):2146-2157, 2016. [doi]

A Pulse Model in Log-domain for a Uniform SynthesizerGilles Degottex, Pierre Lanchantin, Mark J. F. Gales. ssw 2016: 214-220 [doi]

Incorporating a Generative Front-End Layer to Deep Neural Network for Noise Robust Automatic Speech RecognitionSouvik Kundu, Khe Chai Sim, Mark J. F. Gales. interspeech 2016: 2359-2363 [doi]

Selection of Multi-Genre Broadcast Data for the Training of Automatic Speech Recognition SystemsPierre Lanchantin, Mark J. F. Gales, Penny Karanasou, X. Liu, Y. Qian, L. Wang, Philip C. Woodland, C. Zhang. interspeech 2016: 3057-3061 [doi]

Towards Using Conversations with Spoken Dialogue Systems in the Automated Assessment of Non-Native Speakers of EnglishDiane Litman, Steve J. Young, Mark J. F. Gales, Kate Knill, Karen Ottewell, Rogier C. van Dalen, David Vandyke. sigdial 2016: 270-275 [doi]

Two Efficient Lattice Rescoring Methods Using Recurrent Neural Network Language ModelsXunying Liu, Xie Chen, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland. taslp, 24(8):1438-1449, 2016. [doi]

Off-topic Response Detection for Spontaneous Spoken English AssessmentAndrey Malinin, Rogier C. van Dalen, Kate Knill, Yu Wang, Mark J. F. Gales. acl 2016: [doi]

Multi-Language Neural Network Language ModelsAnton Ragni, Edgar Dakin, Xie Chen, Mark J. F. Gales, Kate M. Knill. interspeech 2016: 3042-3046 [doi]

Improved DNN-based segmentation for multi-genre broadcast audioLinlin Wang, Chao Zhang, Philip C. Woodland, Mark J. F. Gales, Panagiota Karanasou, Pierre Lanchantin, Xunying Liu, Yanmin Qian. icassp 2016: 5700-5704 [doi]

Sequence Student-Teacher Training of Deep Neural NetworksJeremy H. M. Wong, Mark J. F. Gales. interspeech 2016: 2761-2765 [doi]

Stimulated Deep Neural Network for Speech RecognitionChunyang Wu, Penny Karanasou, Mark J. F. Gales, Khe Chai Sim. interspeech 2016: 400-404 [doi]

Combining i-vector representation and structured neural networks for rapid adaptationChunyang Wu, Penny Karanasou, Mark J. F. Gales. icassp 2016: 5000-5004 [doi]

Log-Linear System Combination Using Structured Support Vector MachinesJingzhou Yang, Anton Ragni, Mark J. F. Gales, Kate M. Knill. interspeech 2016: 1898-1902 [doi]

System combination with log-linear modelsJ. Yang, C. Zhang, Anton Ragni, Mark J. F. Gales, Philip C. Woodland. icassp 2016: 5675-5679 [doi]

2015

The MGB challenge: Evaluating multi-genre broadcast media recognitionPeter Bell 0001, Mark J. F. Gales, Thomas Hain, Jonathan Kilgour, Pierre Lanchantin, Xunying Liu, Andrew McParland, Steve Renals, Oscar Saz, Mirjam Wester, Philip C. Woodland. asru 2015: 687-693 [doi]

Speaker and Expression Factorization for Audiobook Data: Expressiveness and TransplantationLangzhou Chen, Norbert Braunschweiler, Mark J. F. Gales. taslp, 23(4):605-618, 2015. [doi]

Recurrent neural network language model training with noise contrastive estimation for speech recognitionXie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland. icassp 2015: 5411-5415 [doi]

Investigation of back-off based interpolation between recurrent neural network and n-gram language modelsXie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland. asru 2015: 181-186 [doi]

Improving the training and evaluation efficiency of recurrent neural network language modelsXie Chen, Xunying Liu, Mark J. F. Gales, Philip C. Woodland. icassp 2015: 5401-5405 [doi]

Recurrent neural network language model adaptation for multi-genre broadcast speech recognitionX. Chen, T. Tan, Xunying Liu, Pierre Lanchantin, M. Wan, Mark J. F. Gales, Philip C. Woodland. interspeech 2015: 3511-3515 [doi]

Robust excitation-based features for Automatic Speech RecognitionThomas Drugman, Yannis Stylianou, Langzhou Chen, Xie Chen, Mark J. F. Gales. icassp 2015: 4664-4668 [doi]

Unicode-based graphemic systems for limited resource languagesMark J. F. Gales, Kate M. Knill, Anton Ragni. icassp 2015: 5186-5190 [doi]

I-vector estimation using informative priors for adaptation of deep neural networksPenny Karanasou, Mark J. F. Gales, Philip C. Woodland. interspeech 2015: 2872-2876 [doi]

Speaker diarisation and longitudinal linking in multi-genre broadcast dataPenny Karanasou, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang. asru 2015: 660-666 [doi]

Reconstructing voices within the multiple-average-voice-model frameworkPierre Lanchantin, Christophe Veaux, Mark J. F. Gales, Simon King, Junichi Yamagishi. interspeech 2015: 2232-2236 [doi]

The development of the cambridge university alignment systems for the multi-genre broadcast challengePierre Lanchantin, Mark J. F. Gales, Penny Karanasou, Xunying Liu, Yanmin Qian, Linlin Wang, Philip C. Woodland, Chao Zhang. asru 2015: 647-653 [doi]

Paraphrastic recurrent neural network language modelsXunying Liu, Xie Chen, Mark J. F. Gales, Philip C. Woodland. icassp 2015: 5406-5410 [doi]

The cambridge university 2014 BOLT conversational telephone Mandarin Chinese LVCSR system for speech translationXunying Liu, Federico Flego, Linlin Wang, C. Zhang, Mark J. F. Gales, Philip C. Woodland. interspeech 2015: 3145-3149 [doi]

Improving speech recognition and keyword search for low resource languages using web dataGideon Mendels, Erica Cooper, Victor Soto, Julia Hirschberg, Mark J. F. Gales, Kate M. Knill, Anton Ragni, Haipeng Wang. interspeech 2015: 829-833 [doi]

A language space representation for speech recognitionAnton Ragni, Mark J. F. Gales, Kate M. Knill. icassp 2015: 4634-4638 [doi]

Improving the interpretability of deep neural networks with stimulated learningShawn Tan, Khe Chai Sim, Mark J. F. Gales. asru 2015: 617-623 [doi]

Automatically grading learners' English using a Gaussian processRogier C. van Dalen, Kate M. Knill, Mark J. F. Gales. slte 2015: 7-12 [doi]

Annotating large lattices with the exact word errorRogier C. van Dalen, Mark J. F. Gales. interspeech 2015: 2625-2629 [doi]

Improving multiple-crowd-sourced transcriptions using a speech recogniserRogier C. van Dalen, Kate M. Knill, Pirros Tsiakoulis, Mark J. F. Gales. icassp 2015: 4709-4713 [doi]

Structured discriminative models using deep neural-network featuresRogier C. van Dalen, Jingzhou Yang, Haipeng Wang, Anton Ragni, Chao Zhang, Mark J. F. Gales. asru 2015: 160-166 [doi]

Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languagesHaipeng Wang, Anton Ragni, Mark J. F. Gales, Kate M. Knill, Philip C. Woodland, Chao Zhang. interspeech 2015: 3660-3664 [doi]

Cambridge university transcription systems for the multi-genre broadcast challengePhilip C. Woodland, Xunying Liu, Yanmin Qian, Chao Zhang, Mark J. F. Gales, Penny Karanasou, Pierre Lanchantin, Linlin Wang. asru 2015: 639-646 [doi]

Multi-basis adaptive neural network for rapid adaptation in speech recognitionChunyang Wu, Mark J. F. Gales. icassp 2015: 4315-4319 [doi]

Environmentally robust ASR front-end for deep neural network acoustic modelsTakuya Yoshioka, Mark J. F. Gales. csl, 31(1):65-86, 2015. [doi]

2014

Integrated Expression Prediction and Speech Synthesis From TextLangzhou Chen, Mark J. F. Gales, Norbert Braunschweiler, Masami Akamine, Kate Knill. jstsp, 8(2):323-335, 2014. [doi]

Efficient GPU-based training of recurrent neural network language models using spliced sentence bunchXie Chen, Yongqiang Wang, Xunying Liu, Mark J. F. Gales, Philip C. Woodland. interspeech 2014: 641-645 [doi]

An initial investigation of long-term adaptation for meeting transcriptionX. Chen, Mark J. F. Gales, Kate M. Knill, Catherine Breslin, Langzhou Chen, K. K. Chin, Vincent Wan. interspeech 2014: 954-958 [doi]

Speaker dependent expression predictor from text: Expressiveness and transplantationLangzhou Chen, Norbert Braunschweiler, Mark J. F. Gales. icassp 2014: 2574-2578 [doi]

Speech recognition and keyword spotting for low-resource languages: Babel project research at CUEDMark J. F. Gales, Kate M. Knill, Anton Ragni, Shakti P. Rath. sltu 2012: 16-23 [doi]

Adaptation of deep neural network acoustic models using factorised i-vectorsPenny Karanasou, Yongqiang Wang, Mark J. F. Gales, Philip C. Woodland. interspeech 2014: 2180-2184 [doi]

Language independent and unsupervised acoustic models for speech recognition and keyword spottingKate Knill, Mark J. F. Gales, Anton Ragni, Shakti P. Rath. interspeech 2014: 16-20 [doi]

Generating multiple-accent pronunciations for TTS using joint sequence model interpolationBalaKrishna Kolluru, Vincent Wan, Javier Latorre, Kayoko Yanagisawa, Mark J. F. Gales. interspeech 2014: 1273-1277 [doi]

Multiple-average-voice-based speech synthesisPierre Lanchantin, Mark J. F. Gales, Simon King, Junichi Yamagishi. icassp 2014: 285-289 [doi]

Speech intonation for TTS: study on evaluation methodologyJavier Latorre, Kayoko Yanagisawa, Vincent Wan, BalaKrishna Kolluru, Mark J. F. Gales. interspeech 2014: 2957-2961 [doi]

Paraphrastic language modelsXunying Liu, Mark J. F. Gales, Philip C. Woodland. csl, 28(6):1298-1316, 2014. [doi]

Paraphrastic neural network language modelsXunying Liu, Mark J. F. Gales, Philip C. Woodland. icassp 2014: 4903-4907 [doi]

Efficient lattice rescoring using recurrent neural network language modelsXunying Liu, Yongqiang Wang, Xie Chen, Mark J. F. Gales, Philip C. Woodland. icassp 2014: 4908-4912 [doi]

Data augmentation for low resource languagesAnton Ragni, Kate M. Knill, Shakti P. Rath, Mark J. F. Gales. interspeech 2014: 810-814 [doi]

Combining tandem and hybrid systems for improved speech recognition and keyword spotting on low resource languagesShakti P. Rath, Kate M. Knill, Anton Ragni, Mark J. F. Gales. interspeech 2014: 835-839 [doi]

Building HMM-TTS Voices on Diverse DataVincent Wan, Javier Latorre, Kayoko Yanagisawa, Norbert Braunschweiler, Langzhou Chen, Mark J. F. Gales, Masami Akamine. jstsp, 8(2):296-306, 2014. [doi]

Cluster adaptive training of average voice modelsVincent Wan, Javier Latorre, Kayoko Yanagisawa, Mark J. F. Gales, Yannis Stylianou. icassp 2014: 280-284 [doi]

Noise-robust TTS speaker adaptation with statistics smoothingKayoko Yanagisawa, Langzhou Chen, Mark J. F. Gales. interspeech 2014: 1519-1523 [doi]

Infinite structured support vector machines for speech recognitionJingzhou Yang, Rogier C. van Dalen, Shi-Xiong Zhang, Mark J. F. Gales. icassp 2014: 3320-3324 [doi]

Investigation of unsupervised adaptation of DNN acoustic models with filter bank inputTakuya Yoshioka, Anton Ragni, Mark J. F. Gales. icassp 2014: 6344-6348 [doi]

Impact of single-microphone dereverberation on DNN-based meeting transcription systemsTakuya Yoshioka, Xie Chen, Mark J. F. Gales. icassp 2014: 5527-5531 [doi]

2013

Integrated automatic expression prediction and speech synthesis from textLangzhou Chen, Mark J. F. Gales, Norbert Braunschweiler, Masami Akamine, Kate Knill. icassp 2013: 7977-7981 [doi]

A high-performance Cantonese keyword search systemBrian 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. icassp 2013: 8277-8281 [doi]

Training a supra-segmental parametric F0 model without interpolating F0Javier Latorre, Mark J. F. Gales, Kate Knill, Masami Akamine. icassp 2013: 6880-6884 [doi]

Language model cross adaptation for LVCSR system combinationXunying Liu, Mark J. F. Gales, Philip C. Woodland. csl, 27(4):928-942, 2013. [doi]

Cross-domain paraphrasing for improving language modelling using out-of-domain dataXunying Liu, Mark J. F. Gales, Philip C. Woodland. interspeech 2013: 3424-3428 [doi]

Improving lightly supervised training for broadcast transcriptionYanhua Long, Mark J. F. Gales, Pierre Lanchantin, Xunying Liu, Matthew Stephen Seigel, Philip C. Woodland. interspeech 2013: 2187-2191 [doi]

Complex cepstrum for statistical parametric speech synthesisRanniery Maia, Masami Akamine, Mark J. F. Gales. speech, 55(5):606-618, 2013. [doi]

System combination and score normalization for spoken term detectionJonathan 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. icassp 2013: 8272-8276 [doi]

Efficient decoding with generative score-spaces using the expectation semiringRogier C. van Dalen, Anton Ragni, Mark J. F. Gales. icassp 2013: 7619-7623 [doi]

Noise robustness in HMM-TTS speaker adaptationKayoko Yanagisawa, Javier Latorre, Vincent Wan, Mark J. F. Gales, Simon King. ssw 2013: 119-124 [doi]

Structured SVMs for Automatic Speech RecognitionShi-Xiong Zhang, Mark J. F. Gales. taslp, 21(3):544-555, 2013. [doi]

All Publications

Filter by Year

[-]
OR AND NOT 1

Filter by Type
OR AND NOT 1

Filter by Tag
OR AND NOT 1

Filter by Venue

[+]
OR AND NOT 1

Filter by Author

[+]
OR AND NOT 1

Filter by Top Terms

[+]
OR AND NOT 1

Researchr

Publications by 'Mark J. F. Gales'

Viewing Publication 1 - 100 from 223

2019

2018

2017

2016

2015

2014

2013

All Publications

Filter by Year [-]OR AND NOT 1

Filter by TypeOR AND NOT 1

Filter by TagOR AND NOT 1

Filter by Venue [+]OR AND NOT 1

Filter by Author [+]OR AND NOT 1

Filter by Top Terms [+]OR AND NOT 1

Researchr

Publications by 'Mark J. F. Gales'

Viewing Publication 1 - 100 from 223

2019

2018

2017

2016

2015

2014

2013

Filter by Year

[-]
OR AND NOT 1

Filter by Type
OR AND NOT 1

Filter by Tag
OR AND NOT 1

Filter by Venue

[+]
OR AND NOT 1

Filter by Author

[+]
OR AND NOT 1

Filter by Top Terms

[+]
OR AND NOT 1