Department of Engineering

Prof. Mark Gales - Publications

Number of items: 421.

Article

Chen, X and Liu, X and Wang, Y and Ragni, A and Wong, JHM and Gales, MJF (2019) Exploiting Future Word Contexts in Neural Network Language Models for Speech Recognition. IEEE/ACM Transactions on Audio Speech and Language Processing, 27. pp. 1444-1454. ISSN 2329-9290

Li, Q and Ness, PM and Ragni, A and Gales, MJF (2019) Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation. ISSN 1520-6149

Wong, JHM and Gales, MJF and Wang, Y (2019) General sequence teacher-student learning. IEEE/ACM Transactions on Audio Speech and Language Processing, 27. pp. 1725-1736. ISSN 2329-9290

Wang, Y and Gales, MJF and Knill, KM and Kyriakopoulos, K and Malinin, A and van Dalen, RC and Rashid, M (2018) Towards automatic assessment of spontaneous spoken English. Speech Communication, 104. pp. 47-56. ISSN 0167-6393

Degottex, G and Lanchantin, P and Gales, M (2017) A Log Domain Pulse Model for Parametric Speech Synthesis. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26. pp. 57-70. ISSN 2329-9290

Chen, X and Liu, X and Ragni, A and Wang, Y and Gales, MJF (2017) Future word contexts in neural network language models. 2017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017 - Proceedings, 2018-J. pp. 97-103.

Karanasou, P and Wu, C and Gales, M and Woodland, PC (2017) I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models. IEEE/ACM Transactions on Audio Speech and Language Processing, 25. pp. 818-828. ISSN 2329-9290

Wu, C and Gales, M and Ragni, A and Karanasou, P and Sim, KC (2017) Improving Interpretability and Regularisation in Deep Learning. IEEE/ACM Transactions on Audio Speech and Language Processing, 26. pp. 256-265. ISSN 2329-9290

Liu, X and Chen, X and Wang, Y and Gales, MJF and Woodland, PC (2016) Two efficient lattice rescoring methods using recurrent neural network language models. IEEE/ACM Transactions on Audio Speech and Language Processing, 24. pp. 1438-1449. ISSN 2329-9290

Chen, X and Liu, X and Wang, Y and Gales, MJF and Woodland, PC (2016) Efficient Training and Evaluation of Recurrent Neural Network Language Models for Automatic Speech Recognition. IEEE/ACM Transactions on Audio Speech and Language Processing, 24. pp. 2146-2157. ISSN 2329-9290

Yoshioka, T and Gales, MJF (2015) Environmentally robust ASR front-end for deep neural network acoustic models. Computer Speech and Language, 31. pp. 65-86. ISSN 0885-2308

Chen, L and Braunschweiler, N and Gales, MJF (2015) Speaker and Expression Factorization for Audiobook Data: Expressiveness and Transplantation. IEEE Transactions on Audio, Speech and Language Processing, 23. pp. 605-618. ISSN 1558-7916

Wan, V and Latorre, J and Yanagisawa, K and Braunschweiler, N and Chen, L and Gales, MJF and Akamine, M (2014) Building HMM-TTS voices on diverse data. IEEE Journal on Selected Topics in Signal Processing, 8. pp. 296-306. ISSN 1932-4553

Chen, L and Gales, MJF and Braunschweiler, N and Akamine, M and Knill, K (2014) Integrated expression prediction and speech synthesis from text. IEEE Journal on Selected Topics in Signal Processing, 8. pp. 323-335. ISSN 1932-4553

Lanchantin, P and Gales, MJF and King, S and Yamagishi, J (2014) Multiple-average-voice-based speech synthesis. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 285-289. ISSN 1520-6149

Liu, X and Gales, MJF and Woodland, PC (2014) Paraphrastic language models. Computer Speech and Language, 28. pp. 1298-1316. ISSN 0885-2308

Maia, R and Akamine, M and Gales, MJF (2013) Complex cepstrum for statistical parametric speech synthesis. SPEECH COMMUNICATION, 55. pp. 606-618. ISSN 0167-6393

Zhang, S-X and Gales, MJF (2013) Structured SVMs for Automatic Speech Recognition. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 21. pp. 544-555. ISSN 1558-7916

Liu, X and Gales, MJF and Woodland, PC (2013) Paraphrastic language models and combination with neural network language models. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 8421-8425. ISSN 1520-6149

Mamou, J and Cui, J and Cui, X and Gales, MJF and Kingsbury, B and Knill, K and Mangu, L and Nolden, D and Picheny, M and Ramabhadran, B and Schluter, R and Sethy, A and Woodland, PC (2013) System combination and score normalization for spoken term detection. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 8272-8276. ISSN 1520-6149

Wang, YQ and Gales, MJF (2013) Tandem system adaptation using multiple linear feature transforms. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 7932-7936. ISSN 1520-6149

Seigel, MS and Woodland, PC and Gales, MJF (2013) A confidence-based approach for improving keyword hypothesis scores. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 8565-8569. ISSN 1520-6149

Kingsbury, B and Cui, J and Cui, X and Gales, MJF and Knill, K and Mamou, J and Mangu, L and Nolden, D and Picheny, M and Ramabhadran, B and Schluter, R and Sethy, A and Woodland, PC (2013) A high-performance Cantonese keyword search system. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 8277-8281. ISSN 1520-6149

Liu, X and Hieronymus, JL and Gales, MJF and Woodland, PC (2013) Syllable language models for Mandarin speech recognition: exploiting character language models. J Acoust Soc Am, 133. pp. 519-528.

Long, Y and Gales, MJF and Lanchantin, P and Liu, X and Seigel, MS and Woodland, PC (2013) Improving lightly supervised training for broadcast transcription. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 2187-2191. ISSN 2308-457X

Yang, J and Van Dalen, RC and Gales, M (2013) Infinite support vector machines in speech recognition. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 3303-3307. ISSN 2308-457X

Liu, X and Gales, MJF and Woodland, PC (2013) Language model cross adaptation for LVCSR system combination. Computer Speech and Language, 27. pp. 928-942. ISSN 0885-2308

Liu, X and Gales, MJF and Woodland, PC (2013) Use of contexts in language model interpolation and adaptation. Computer Speech and Language, 27. pp. 301-321. ISSN 0885-2308

van Dalen, RC and Gales, MJF (2013) Importance sampling to compute likelihoods of noise-corrupted speech. COMPUTER SPEECH AND LANGUAGE, 27. pp. 322-349. ISSN 0885-2308

Wang, Y and Gales, MJF (2012) Speaker and Noise Factorization for Robust Speech Recognition. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 20. pp. 2149-2158. ISSN 1558-7916

Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2012) Morphological decomposition in Arabic ASR systems. Computer Speech and Language, 26. pp. 229-243. ISSN 0885-2308

Zen, H and Braunschweiler, N and Buchholz, S and Gales, MJF and Knill, K and Krstulović, S and Latorre, J (2012) Statistical parametric speech synthesis based on speaker and language factorization. IEEE Transactions on Audio, Speech and Language Processing, 20. pp. 1713-1724. ISSN 1558-7916

Zen, H and Gales, MJF and Nankaku, Y and Tokuda, K (2012) Product of Experts for Statistical Parametric Speech Synthesis. IEEE Transactions on Audio, Speech and Language Processing, 20. pp. 794-805. ISSN 1558-7916

Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2012) Morphological decomposition in Arabic ASR systems. Computer Speech and Language.

Liu, X and Gales, MJF and Woodland, PC (2012) Paraphrastic language models. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, 2. pp. 1654-1657.

Bell, PJ and Gales, MJF and Lanchantin, P and Liu, X and Long, Y and Renals, S and Swietojanski, P and Woodland, PC (2012) Transcription of multi-genre media archives using out-of-domain data. 2012 IEEE Workshop on Spoken Language Technology, SLT 2012 - Proceedings. pp. 324-329.

Flego, F and Gales, MJF (2012) Factor analysis based VTS discriminative adaptive training. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4669-4672. ISSN 1520-6149

Gales, MJF and Watanabe, S and Fosler-Lussier, E (2012) Structured discriminative models for speech recognition: An overview. IEEE Signal Processing Magazine, 29. pp. 70-81. ISSN 1053-5888

Gales, MJF and Flego, F and Association, ISC (2012) Model-Based Approaches for Degraded Channel Modelling in Robust ASR. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3. pp. 1198-1201.

Kim, D and Gales, MJF (2011) Noisy constrained maximum-likelihood linear regression for noise-robust speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 19. pp. 315-325. ISSN 1558-7916

Park, J and Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2011) The efficient incorporation of MLP features into automatic speech recognition systems. Computer Speech and Language, 25. pp. 519-534. ISSN 0885-2308

Chen, L and Gales, MJF and Chin, KK (2011) Constrained discriminative mapping transforms for unsupervised speaker adaptation. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 5344-5347. ISSN 1520-6149

Latorre, J and Gales, MJF and Buchholz, S and Knill, K and Tamura, M and Ohtani, Y and Akamine, M (2011) Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification? ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4724-4727. ISSN 1520-6149

Zen, H and Gales, MJF (2011) Decision tree-based context clustering based on cross validation and hierarchical priors. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4560-4563. ISSN 1520-6149

Flego, F and Gales, MJF (2011) Factor analysis based VTS and JUD noise estimation and compensation. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4792-4795. ISSN 1520-6149

Liu, X and Gales, MJF and Hieronymus, JL and Woodland, PC (2011) Investigation of acoustic units for LVCSR systems. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4872-4875. ISSN 1520-6149

Chin, KK and Xu, H and Gales, MJF and Breslin, C and Knill, K (2011) Rapid joint speaker and noise compensation for robust speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 5500-5503. ISSN 1520-6149

Wang, YQ and Gales, MJF (2011) Speaker and noise factorisation on the AURORA4 task. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4584-4587. ISSN 1520-6149

Ragni, A and Gales, MJF (2011) Structured discriminative models for noise robust continuous speech recognition. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 4788-4791. ISSN 1520-6149

Gales, MJF and Wang, YQ (2011) Model-based approaches to handling additive noise in reverberant environments. 2011 Joint Workshop on Hands-free Speech Communication and Microphone Arrays, HSCMA'11. pp. 121-126.

Xu, HT and Gales, MJF and Chin, KK (2011) Joint Uncertainty Decoding With Predictive Methods for Noise Robust Speech Recognition. IEEE T AUDIO SPEECH, 19. pp. 1665-1676. ISSN 1558-7916

Van Dalen, RC and Gales, MJF (2011) Extended VTS for noise-robust speech recognition. IEEE Transactions on Audio, Speech and Language Processing, 19. pp. 733-743. ISSN 1558-7916

Ragni, A and Gales, MJF (2011) Derivative kernels for noise robust ASR. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. pp. 119-124.

Zhang, SX and Gales, MJF (2011) Extending noise robust structured support vector machines to larger vocabulary tasks. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. pp. 18-23.

Li, T and Woodland, PC and Diehl, F and Gales, MJF (2011) Graphone model interpolation and Arabic pronunciation generation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 2309-2312.

Liu, X and Gales, MJF and Woodland, PC (2011) Improving LVCSR system combination using neural network language model cross adaptation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 2857-2860.

Wang, YQ and Gales, MJF (2011) Improving reverberant VTS for hands-free robust speech recognition. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. pp. 113-118.

Breslin, C and Chin, KK and Gales, MJF and Knill, K (2011) Integrated online speaker clustering and adaptation. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 1085-1088.

Dieh, F and Gales, MJF and Liu, X and Tomalin, M and Woodland, PC (2011) Word boundary modelling and full covariance gaussians for Arabic Speech-to-Text systems. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 777-780.

Van Dalen, RC and Gales, MJF (2011) A variational perspective on noise-robust speech recognition. 2011 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2011, Proceedings. pp. 125-130.

Gales, MJF and Flego, F (2010) Discriminative classifiers with adaptive kernels for noise robust speech recognition. Computer Speech and Language, 24. pp. 648-662. ISSN 0885-2308

Yu, K and Gales, MJF and Wang, L and Woodland, PC (2010) Unsupervised training and directed manual transcription for LVCSR. Speech Communication, 52. pp. 652-663. ISSN 0167-6393

Yu, K and Gales, M and Wang, L and Woodland, PC (2010) Unsupervised training and directed manual transcription for LVCSR. SPEECH COMMUN, 52. pp. 652-663. ISSN 0167-6393

Liu, X and Gales, MJF and Hieronymus, JL and Woodland, PC (2010) Language model combination and adaptation using weighted finite state transducers. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. pp. 5390-5393. ISSN 1520-6149

Zhang, SX and Ragni, A and Gales, MJF (2010) Structured Log Linear Models for Noise Robust Speech Recognition. IEEE SIGNAL PROC LET, 17. pp. 945-948. ISSN 1070-9908

Longworth, C and Gales, MJF (2009) Combining derivative and parametric kernels for speaker verification. IEEE Transactions on Audio Speech and Language Processing, 17. pp. 748-757. ISSN 1558-7916

Breslin, C and Gales, MJF (2009) Directed decision trees for generating complementary systems. Speech Communication, 51. pp. 284-295. ISSN 0167-6393

Yu, K and Gales, MJF and Woodland, PC (2009) Unsupervised adaptation with discriminative mapping transforms. IEEE Transactions on Audio Speech and Language Processing, 17. pp. 714-723. ISSN 1558-7916

Hieronymus, JL and Liu, X and Gales, MJF and Woodland, PC (2009) Exploiting Chinese character models to improve speech recognition performance. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. pp. 364-367.

Liao, H and Gales, MJF (2008) Issues with uncertainty decoding for noise robust automatic speech recognition. Speech Communication, 50. pp. 265-277. ISSN 0167-6393

Layton, M and Gales, MJF (2007) Acoustic modelling using continuous rational kernels. Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, 48. pp. 67-82. ISSN 0922-5773

Liu, X and Gales, MJF (2007) Automatic model complexity control using marginalized discriminative growth functions. IEEE Transactions on Audio Speech and Language Processing, 15. pp. 1414-1424. ISSN 1558-7916

Yu, K and Gales, MJF (2007) Bayesian adaptive inference and adaptive training. IEEE Transactions on Audio Speech and Language Processing, 15. pp. 1932-1943. ISSN 1558-7916

Sim, KC and Gales, MJF (2007) Discriminative semi-parametric trajectory models for speech recognition. Computer Speech and Language, 21. pp. 669-687. ISSN 0885-2308

Gales, MJF and Young, SJ (2007) The application of hidden Markov models in speech recognition. Foundations and Trends in Signal Processing, 1. pp. 195-304. ISSN 1932-8346

Tomalin, M and Gales, MJF and Liu, XA and Sim, KC and Sinha, R and Wang, L and Woodland, PC and Yu, K (2007) Improving speech transcription for Mandarin-english translation. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 4. ISSN 1520-6149

Liu, X and Gales, M (2007) Automatic model complexity control using marginalized discriminative growth functions. IEEE Transactions on Audio, Speech and Language Processing, 15. pp. 1414-1424. ISSN 1558-7916

Yu, K and Gales, MJF (2006) Discriminative cluster adaptive training. IEEE Transactions on Audio Speech and Language Processing, 14. pp. 1694-1703. ISSN 1558-7916

Young, SJ and Evermann, G and Gales, MJF and Kershaw, D and Moore, G and Odell, JJ and Ollason, DG and Povey, D and Valtchev, V and Woodland, PC (2006) The HTK book version 3.4.

Sim, KC and Gales, MJF (2006) Minimum phone error training of precision matrix models. IEEE Transactions on Audio Speech and Language Processing, 14. pp. 882-889. ISSN 1558-7916

Gales, MJF and Airey, SS (2006) Product of Gaussians for speech recognition. Computer Speech and Language, 20. pp. 22-40. ISSN 0885-2308

Gales, MJF and Kim, DY and Woodland, PC and Chan, HY and Mrva, D and Sinha, R and Tranter, SE (2006) Progress in the CU-HTK broadcast news transcription system. IEEE Transactions on Speech and Audio Processing, 14. pp. 1513-1525. ISSN 1063-6676

Gales, MJF and Layton, MI (2006) Training augmented models using SVMs. IEICE Transactions on Information and Systems, E89-D. pp. 892-899. ISSN 0916-8532

Hain, T and Woodland, PC and Evermann, G and Gales, MJF and Liu, X and Moore, GL and Povey, D and Wang, L (2006) Corrections to “Automatic transcription of conversational telephone speech”. IEEE Transactions on Audio, Speech and Language Processing, 14. 727-. ISSN 1558-7916

Sinha, R and Gales, MJF and Kim, DY and Liu, XA and Sim, KC and Woodland, PC (2006) The CU-HTK Mandarin broadcast news transcription system. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 1. ISSN 1520-6149

Hain, T and Woodland, PC and Evermann, G and Gales, MJF and Liu, X and Moore, GL and Povey, D and Wang, L (2005) Automatic transcription of conversational telephone speech. IEEE Transactions on Speech and Audio Processing, 13. pp. 1173-1185. ISSN 1063-6676

Sinha, R and Tranter, SE and Gales, MJF and Woodland, PC (2005) The Cambridge University March 2005 Speaker Diarisation System. Interspeech: 9th European Conference on Speech Communciation and Technology. pp. 2437-2440. ISSN 1018-4074

Hain, T and Woodland, PC and Evermann, G and Gales, MJF and Liu, X and Moore, GL and Povey, D and Wang, L (2005) Automatic transcription of conversational telephone speech. IEEE Transactions on Speech and Audio Processing, 13. pp. 1173-1185. ISSN 1063-6676

Rosti, AVI and Gales, MJF (2004) Factor analysed hidden Markov models for speech recognition. Computer Speech and Language, 18. pp. 181-200. ISSN 0885-2308

Povey, D and Gales, MJF and Kim, DY and Woodland, PC (2003) MMI-MAP and MPE-MAP for acoustic model adaptation. Eurospeech Proceedings: 8th Speech Communication and Technology Conference, 8. pp. 1981-1984. ISSN 1018-4074

Chen, SS and Eide, EM and Gales, MJF and Gopinath, RA and Kanevsky, D and Olsen, P (2002) Automatic transcription of broadcast news. Speech communication, 37. pp. 69-87. ISSN 0167-6393

Gales, MJF (2002) Maximum likelihood multiple subspace projections for hidden markov models. IEEE transactions on Speech and Audio Processing, 10. pp. 37-47. ISSN 1063-6676

Gales, MJF (2002) Transformation streams and the HMM error model. Computer Speech and Language, 16. pp. 225-243. ISSN 0885-2308

Gales, MJF (2002) Transformation streams and the HMM error model. COMPUT SPEECH LANG, 16. pp. 225-243. ISSN 0885-2308

Gales, MJF (2000) Cluster adaptive training of hidden markov models. IEEE Transactions on Speech and Audio Processing, 8. pp. 417-428. ISSN 1063-6676

Gales, MJF (2000) Factored semi-tied covariance matrices. Advances In Neural Information Processing Systems. pp. 779-785. ISSN 1049-5258

Gales, MJF (2000) Factored semi-tied covariance matrices. Advances In Neural Information Processing Systems. pp. 779-785. ISSN 1049-5258

Gales, MJF (1999) Semi-tied covariance matrices for hidden markov models. IEEE Transactions on Speech and Audio Processing, 7. pp. 272-281. ISSN 1063-6676

Gales, MJF and Knill, K and Young, SJ (1999) State-based Gaussian selection in large vocabulary continuous speech recognition using HMMs. IEEE Transactions on Speech and Audio Processing, 7. pp. 152-161. ISSN 1063-6676

Gales, MJF (1998) Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech and Language, 12. pp. 75-98. ISSN 0885-2308

Gales, MJF (1998) Predictive model-based compensation schemes for robust speech recognition. Speech Communication, 25. pp. 49-74. ISSN 0167-6393

Gales, MJF (1997) Predictive model-based compensation schemes for robust speech recognition. Speech Communication, 25. pp. 49-74. ISSN 0167-6393

Gales, MJF and Woodland, PC (1996) Mean and variance adaptation within the MLLR framework. Computer Speech and Language, 10. pp. 249-264. ISSN 0885-2308

Gales, MJF and Young, SJ (1996) Robust continuous speech recognition using parallel model combination. IEEE Proceedings on Speech and Audio Processing, 4. pp. 352-359. ISSN 1063-6676

Woodland, PC and Gales, MJF and Pye, D and Valtchev, V (1995) Large vocabulary multilingual speech recognition using HTK. Eurospeech Proceedings: 4th European Conference on Speech Communication and Technology, 1. pp. 181-184. ISSN 1018-4074

Gales, MJF and Young, SJ (1995) Robust speech recognition in additive and convolutional noise using parallel model combination. Computer Speech and Language, 9. pp. 289-308. ISSN 0885-2308

GALES, MJF and YOUNG, SJ (1993) CEPSTRAL PARAMETER COMPENSATION FOR HMM RECOGNITION IN NOISE. SPEECH COMMUN, 12. pp. 231-239. ISSN 0167-6393

Dou, Q and Lu, Y and Efiong, J and Gales, MJF Attention Forcing for Sequence-to-sequence Model Training. (Unpublished)

Wu, C and Gales, M and Ragni, A and Karanasou, P and Sim, KC Improving Interpretability and Regularisation in Deep Learning. (Unpublished)

Wang, L and Wang, Y and Gales, MJF Non-native Speaker Verification for Spoken Language Assessment. (Unpublished)

Book Section

Gales, MJF (2009) Augmented Statistical Models: Using Dynamic Kernels for Acoustic Models. In: Automatic Speech and Speaker Recognition: Large Margin and Kernel Methods. UNSPECIFIED, pp. 83-99.

Conference or Workshop Item

Kyriakopoulos, K and Knill, KM and Gales, MJF (2020) Automatic detection of accent and lexical pronunciation errors in spontaneous non-native English speech. In: Interspeech 2020, 2020-10-25 to 2020-10-29 pp. 3052-3056..

Raina, V and Gales, MJF and Knill, K (2020) Universal adversarial attacks on spoken language assessment systems. In: Interspeech 2020, 2020-10-25 to 2020-10-29 pp. 3855-3859..

Kastanos, A and Ragni, A and Gales, MJF (2020) Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks. In: UNSPECIFIED pp. 6329-6333..

Manakul, P and Gales, MJF and Wang, L (2020) Abstractive spoken document summarization using hierarchical model with multi-stage attention diversity optimization. In: UNSPECIFIED pp. 4248-4252..

Dou, Q and Efiong, J and Gales, MJF (2020) Attention forcing for speech synthesis. In: UNSPECIFIED pp. 4014-4018..

Wu, X and Knill, KM and Gales, MJF and Malinin, A (2020) Ensemble approaches for uncertainty in spoken language assessment. In: UNSPECIFIED pp. 3860-3864..

Knill, KM and Wang, L and Wang, Y and Wu, X and Gales, MJF (2020) Non-native children's automatic speech recognition: The INTERSPEECH 2020 shared task ALTA systems. In: UNSPECIFIED pp. 255-259..

Lu, Y and Gales, MJF and Wang, Y (2020) Spoken language 'grammatical error correction'. In: UNSPECIFIED pp. 3840-3844..

Raina, V and Gales, MJF and Knill, K (2020) Complementary Systems for Off-Topic Spoken Response Detection. In: UNSPECIFIED pp. 41-51..

Knill, KM and Gales, MJF and Manakul, PP and Caines, AP (2019) Automatic Grammatical Error Detection of Non-native Spoken Learner English. In: UNSPECIFIED pp. 8127-8131..

Ragni, A and Li, Q and Gales, MJF and Wang, Y (2019) Confidence Estimation and Deletion Prediction Using Bidirectional Recurrent Neural Networks. In: IEEE Workshop on Spoken Language Technology 2018, 2018-12-18 to 2018-12-21 pp. 204-211..

Dou, Q and Wan, M and Degottex, G and Ma, Z and Gales, MJF (2019) Hierarchical RNNs for Waveform-Level Speech Synthesis. In: UNSPECIFIED pp. 618-625..

Del Vecchio, M and Malinin, A and Gales, MJF (2019) Improved Auto-Marking Confidence for Spoken Language Assessment. In: UNSPECIFIED pp. 957-963..

Wang, Y and Wong, JHM and Gales, MJF and Knill, KM and Ragni, A (2019) Sequence Teacher-Student Training of Acoustic Models for Automatic Free Speaking Language Assessment. In: IEEE Workshop on Spoken Language Technology, 2018-12-18 to 2018-12-21 pp. 994-1000..

Knill, K and Gales, M and Manakul, P and Caines, A (2019) Automatic grammatical error detection of non-native spoken learner English. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019-5-12 to 2019-5-17.

Wong, JHM and Gales, MJF and Wang, Y (2019) Learning between Different Teacher and Student Models in ASR. In: UNSPECIFIED pp. 93-99..

Lu, Y and Gales, MJF and Knill, KM and Manakul, P and Wang, L and Wang, Y (2019) Impact of ASR performance on spoken grammatical error detection. In: Interspeech 2019, 2019-9-15 to 2019-7-19 pp. 1876-1880..

Kyriakopoulos, K and Knill, KM and Gales, MJF (2019) A deep learning approach to automatic characterisation of rhythm in non-native English speech. In: UNSPECIFIED pp. 1836-1840..

Malinin, A and Gales, M (2018) Predictive Uncertainty Estimation via Prior Networks. In: NIPS 2018, 2018-12-3 to 2018-12-8, Palais des Congrès de Montréal, Montréal CANADA pp. 7047-7058..

Wang, Y and Chen, X and Gales, MJF and Ragni, A and Wong, JHM (2018) Phonetic and graphemic systems for multi-genre broadcast transcription. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018-4-15 to 2018-4-20, Calgary, Alberta, Canada pp. 5899-5903..

Malinin, A and Knill, K and Gales, MJF (2018) A hierarchical attention based model for off-topic spontaneous spoken response detection. In: 2017 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2017-12-16 to 2017-12-20, Okinawa, Japan pp. 397-403..

Chen, O and Ragni, A and Gales, MJF and Chen, X (2018) Active memory networks for language modeling. In: UNSPECIFIED pp. 3338-3342..

Ragni, A and Gales, MJF (2018) Automatic speech recognition system development in the “wild“. In: ISCA Interspeech 2018, 2018-9-2 to 2018-9-6 pp. 2217-2221..

Knill, KM and Gales, MJF and Kyriakopoulos, K and Malinin, A and Ragni, A and Wang, Y and Caines, AP (2018) Impact of ASR performance on free speaking language assessment. In: INTERSPEECH 2018, 2018-9-2 to 2018-9-6, Hyderabad, India pp. 1641-1645..

Wang, Y and Zhang, C and Gales, MJF and Woodland, PC (2018) Speaker adaptation and adaptive training for jointly optimised tandem systems. In: Interspeech2018, -- to -- pp. 872-876..

Wan, M and Degottex, G and Gales, MJF (2018) Waveform-based speaker representations for speech synthesis. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. 2018, 2018-9-2 to 2018-9-6 pp. 897-901..

Kyriakopoulos, K and Knill, KM and Gales, MJF (2018) A deep learning approach to assessing non-native pronunciation of English using phone distances. In: Interspeech, 2018-9-2 to 2018-9-6 pp. 1626-1630..

Wan, M and Degottex, G and Gales, MJF and IEEE, (2017) Integrated speaker-adaptive speech synthesis. In: 2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2017-12-16 to 2017-12-20, Okinawa, Japan pp. 705-711..

Wong, JHM and Gales, MJF (2017) Multi-task ensembles with teacher-student training. In: UNSPECIFIED pp. 84-90..

Gales, MJF and Knill, KM and Ragni, A (2017) Low-resource speech recognition and keyword-spotting. In: International Conference on Speech and Computer, 2017-9-12 to --, Hatfield, Hertfordshire, UK pp. 3-19..

Knill, KM and Gales, MJF and Kyriakopoulos, K and Ragni, A and Wang, Y (2017) Use of graphemic lexicons for spoken language assessment. In: Interspeech 2017, 2017-8-20 to -- pp. 2774-2778..

Wu, C and Gales, MJF (2017) Deep activation mixture model for speech recognition. In: UNSPECIFIED pp. 1611-1615..

Malinin, A and Ragni, A and Knill, KM and Gales, MJF (2017) Incorporating uncertainty into deep learning for spoken language assessment. In: Annual Meeting of the Association for Computational Linguistics July 30-August 4, 2017, 2017-7-30 to 2017-8-4, Vancouver Canada pp. 45-50..

Chen, X and Ragni, A and Liu, X and Gales, MJF (2017) Investigating bidirectional recurrent neural network language models for speech recognition. In: UNSPECIFIED pp. 269-273..

Wong, JHM and Gales, MJF (2017) Student-teacher training with diverse decision tree ensembles. In: Interspeech, 2017-8-20 to -- pp. 117-121.. (Unpublished)

Degottex, G and Lanchantin, P and Gales, M (2016) A Pulse Model in Log-domain for a Uniform Synthesizer. In: 9th ISCA Speech Synthesis Workshop, 2016-9-13 to 2016-9-15, Sunnyvale, CA, USA pp. 230-236..

Chen, X and Liu, X and Qian, Y and Gales, MJF and Woodland, PC (2016) CUED-RNNLM - An open-source toolkit for efficient training and evaluation of recurrent neural network language models. In: UNSPECIFIED pp. 6000-6004..

Wu, C and Karanasou, P and Gales, MJF (2016) Combining i-vector representation and structured neural networks for rapid adaptation. In: UNSPECIFIED pp. 5000-5004..

Wang, L and Zhang, C and Woodland, PC and Gales, MJF and Karanasou, P and Lanchantin, P and Liu, X and Qian, Y (2016) Improved DNN-based segmentation for multi-genre broadcast audio. In: UNSPECIFIED pp. 5700-5704..

Woodland, PC and Liu, X and Qian, Y and Zhang, C and Gales, MJF and Karanasou, P and Lanchantin, P and Wang, L (2016) Cambridge university transcription systems for the multi-genre broadcast challenge. In: UNSPECIFIED pp. 639-646..

Chen, X and Liu, X and Gales, MJF and Woodland, PC (2016) Investigation of back-off based interpolation between recurrent neural network and n-gram language models. In: UNSPECIFIED pp. 181-186..

Bell, P and Gales, MJF and Hain, T and Kilgour, J and Lanchantin, P and Liu, X and McParland, A and Renals, S and Saz, O and Wester, M and Woodland, PC (2016) The MGB challenge: Evaluating multi-genre broadcast media recognition. In: UNSPECIFIED pp. 687-693..

Karanasou, P and Gales, MJF and Lanchantin, P and Liu, X and Qian, Y and Wang, L and Woodland, PC and Zhang, C (2016) Speaker diarisation and longitudinal linking in multi-genre broadcast data. In: UNSPECIFIED pp. 660-666..

Van Dalen, RC and Yang, J and Wang, H and Ragni, A and Zhang, C and Gales, MJF (2016) Structured discriminative models using deep neural-network features. In: UNSPECIFIED pp. 160-166..

Lanchantin, P and Gales, MJF and Karanasou, P and Liu, X and Qian, Y and Wang, L and Woodland, PC and Zhang, C (2016) The development of the Cambridge university alignment systems for the multi-genre broadcast challenge. In: UNSPECIFIED pp. 647-653..

Ragni, A and Saunders, D and Zahemszky, P and Vasilakes, J and Gales, MJF and Knill, KM (2016) Morph-to-word transduction for accurate and efficient automatic speech recognition and keyword search. In: ICASSP 2017, -- to -- pp. 5770-5774..

Chen, X and Ragni, A and Vasilakes, J and Liu, X and Knill, K and Gales, MJF (2016) Recurrent neural network language models for keyword search. In: The 42nd IEEE International Conference on Acoustics, Speech and Signal Processing, 2017-3-5 to 2017-3-9, New Orleans, LA, USA pp. 5775-5779..

Ragni, A and Wu, C and Gales, MJF and Vasilakes, J and Knill, KM (2016) Stimulated training for automatic speech recognition and keyword search in limited resource conditions. In: ICASSP 2017, -- to -- pp. 4830-4834..

Yang, J and Ragni, A and Gales, MJF and Knill, KM (2016) Log-linear system combination using structured support vector machines. In: UNSPECIFIED pp. 1898-1902..

Ragni, A and Dakin, E and Chen, X and Gales, MJF and Knill, KM (2016) Multi-language neural network language models. In: UNSPECIFIED pp. 3042-3046..

Malinin, A and Van Dalen, RC and Wang, Y and Knill, KM and Gales, MJF (2016) Off-topic response detection for spontaneous spoken English assessment. In: UNSPECIFIED pp. 1075-1084..

Lanchantin, P and Gales, MJF and Karanasou, P and Liu, X and Qian, Y and Wang, L and Woodland, PC and Zhang, C (2016) Selection of multi-genre broadcast data for the training of automatic speech recognition systems. In: UNSPECIFIED pp. 3057-3061..

Wong, JHM and Gales, MJF (2016) Sequence student-teacher training of deep neural networks. In: UNSPECIFIED pp. 2761-2765..

Wu, C and Karanasou, P and Gales, MJF and Sim, KC (2016) Stimulated deep neural network for speech recognition. In: UNSPECIFIED pp. 400-404..

Cui, J and Kingsbury, B and Ramabhadran, B and Sethy, A and Audhkhasi, K and Cui, X and Kislal, E and Mangu, L and Nussbaum-Thom, M and Picheny, M and Tüske, Z and Golik, P and Schluter, R and Ney, H and Gales, MJF and Knill, KM and Ragni, A and Wang, H and Woodland, P (2015) Multilingual representations for low resource speech recognition and keyword search. In: IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 -, 2015-12-13 to 2015-12-17 pp. 259-266..

van, DRC and Knill, KM and Gales, MJF (2015) Automatically Grading Learners’ English Using a Gaussian Process. In: Workshop on Speech and Language Technology in Education, 2015-9-4 to 2015-9-5, Leipzig, Germany pp. 7-12..

Wang, H and Ragni, A and Gales, MJF and Knill, KM and Woodland, PC and Zhang, C (2015) Joint decoding of tandem and hybrid systems for improved keyword spotting on low resource languages. In: Interspeech 2015, 2015-9-6 to 2015-9-10 pp. 3660-3664..

Yang, J and Zhang, C and Ragni, A and Gales, MJF and Woodland, PC (2015) System combination with log-linear models. In: Acoustics, Speech, and Signal Processing (ICASSP), International Conference on, -- to -- pp. 5675-5679..

Van Dalen, RC and Knill, KM and Tsiakoulis, P and Gales, MJF (2015) Improving multiple-crowd-sourced transcriptions using a speech recogniser. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, 2015-4-19 to 2015-4-24, Brisbane, Australia pp. 4709-4713..

Gales, MJF and Knill, KM and Ragni, A (2015) Unicode-based graphemic systems for limited resource languages. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, 2015-4-19 to 2015-4-24 pp. 5186-5190..

Ragni, A and Gales, MJF and Knill, KM (2015) A language space representation for speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, 2015-4-19 to 2015-4-24, Brisbane, Australia pp. 4634-4638..

Van Dalen, RC and Gales, MJF (2015) Annotating large lattices with the exact word error. In: UNSPECIFIED pp. 2625-2629..

Liu, X and Flego, F and Wang, L and Zhang, C and Gales, M and Woodland, P (2015) The Cambridge university 2014 BOLT conversational telephone Mandarin Chinese lvcsr system for speech translation. In: UNSPECIFIED pp. 3145-3149..

Mendels, G and Cooper, E and Soto, V and Hirschberg, J and Gales, M and Knill, K and Ragni, A and Wang, H (2015) Improving speech recognition and keyword search for low resource languages using web data. In: UNSPECIFIED pp. 829-833..

Chen, X and Liu, X and Gales, MJF and Woodland, PC (2015) Improving the training and evaluation efficiency of recurrent neural network language models. In: UNSPECIFIED pp. 5401-5405..

Wu, C and Gales, MJF (2015) Multi-basis adaptive neural network for rapid adaptation in speech recognition. In: UNSPECIFIED pp. 4315-4319..

Liu, X and Chen, X and Gales, MJF and Woodland, PC (2015) Paraphrastic recurrent neural network language models. In: UNSPECIFIED pp. 5406-5410..

Lanchantin, P and Veaux, C and Gales, MJF and King, S and Yamagishi, J (2015) Reconstructing voices within the multiple-average-voice-model framework. In: UNSPECIFIED pp. 2232-2236..

Chen, X and Tan, T and Liu, X and Lanchantin, P and Wan, M and Gales, MJF and Woodland, PC (2015) Recurrent neural network language model adaptation for multi-genre broadcast speech recognition. In: UNSPECIFIED pp. 3511-3515..

Chen, X and Liu, X and Gales, MJF and Woodland, PC (2015) Recurrent neural network language model training with noise contrastive estimation for speech recognition. In: UNSPECIFIED pp. 5411-5415..

Drugman, T and Stylianou, Y and Chen, L and Chen, X and Gales, MJF (2015) Robust excitation-based features for Automatic Speech Recognition. In: UNSPECIFIED pp. 4664-4668..

van Dalen, RC and Knill, KM and Tsiakoulis, P and Gales, MJF and IEEE, (2015) IMPROVING MULTIPLE-CROWD-SOURCED TRANSCRIPTIONS USING A SPEECH RECOGNISER. In: UNSPECIFIED pp. 4709-4713..

Wu, C and Gales, MJF and IEEE, (2015) MULTI-BASIS ADAPTIVE NEURAL NETWORK FOR RAPID ADAPTATION IN SPEECH RECOGNITION. In: UNSPECIFIED pp. 4315-4319..

Liu, X and Chen, X and Gales, MJF and Woodland, PC and IEEE, (2015) PARAPHRASTIC RECURRENT NEURAL NETWORK LANGUAGE. In: UNSPECIFIED pp. 5406-5410..

Drugman, T and Stylianou, Y and Chen, L and Chen, X and Gales, MJF and IEEE, (2015) ROBUST EXCITATION-BASED FEATURES FOR AUTOMATIC SPEECH RECOGNITION. In: UNSPECIFIED pp. 4664-4668..

Rath, SP and Knill, KM and Ragni, A and Gales, MJF (2014) Combining tandem and hybrid systems for improved speech recognition and keyword spotting on low resource languages. In: Interspeech 2014, 2014-9-14 to 2014-9-18 pp. 835-839..

Knill, KM and Gales, MJF and Ragni, A and Rath, SP (2014) Language independent and unsupervised acoustic models for speech recognition and keyword spotting. In: Interspeech 2014, 2014-9-14 to 2014-9-18 pp. 16-20..

Karanasou, P and Wang, Y and Gales, MJF and Woodland, PC (2014) Adaptation of deep neural network acoustic models using factorised i-vectors. In: UNSPECIFIED pp. 2180-2184..

Ragni, A and Knill, KM and Rath, SP and Gales, MJF (2014) Data augmentation for low resource languages. In: UNSPECIFIED pp. 810-814..

Chen, X and Wang, Y and Liu, X and Gales, MJF and Woodland, PC (2014) Efficient GPU-based training of recurrent neural network language models using spliced sentence bunch. In: UNSPECIFIED pp. 641-645..

Liu, X and Wang, Y and Chen, X and Gales, MJF and Woodland, PC (2014) Efficient lattice rescoring using recurrent neural network language models. In: UNSPECIFIED pp. 4908-4912..

Kolluru, BK and Wan, V and Latorre, J and Yanagisawa, K and Gales, MJF (2014) Generating multiple-accent pronunciations for TTS using joint sequence model interpolation. In: UNSPECIFIED pp. 1273-1277..

Yoshioka, T and Chen, X and Gales, MJF (2014) Impact of single-microphone dereverberation on DNN-based meeting transcription systems. In: UNSPECIFIED pp. 5527-5531..

Yang, J and Van Dalen, RC and Zhang, SX and Gales, MJF (2014) Infinite structured support vector machines for speech recognition. In: UNSPECIFIED pp. 3320-3324..

Yoshioka, T and Ragni, A and Gales, MJF (2014) Investigation of unsupervised adaptation of DNN acoustic models with filter bank input. In: UNSPECIFIED pp. 6344-6348..

Yanagisawa, K and Chen, L and Gales, MJF (2014) Noise-robust TTS speaker adaptation with statistics smoothing. In: UNSPECIFIED pp. 1519-1523..

Liu, X and Gales, MJF and Woodland, PC (2014) Paraphrastic neural network language models. In: UNSPECIFIED pp. 4903-4907..

Chen, L and Braunschweiler, N and Gales, MJF (2014) Speaker dependent expression predictor from text: Expressiveness and transplantation. In: UNSPECIFIED pp. 2574-2578..

Latorre, J and Yanagisawa, K and Wan, V and Kolluru, BK and Gales, MJF (2014) Speech intonation for TTS: Study on evaluation methodology. In: UNSPECIFIED pp. 2957-2961..

Chen, X and Gales, MJF and Knill, K and Breslin, C and Chen, L and Chin, KK and Wan, V (2014) An initial investigation of long-term adaptation for meeting transcription. In: UNSPECIFIED pp. 954-958..

Knill, KM and Gales, MJF and Rath, SP and Woodland, PC and Zhang, C and Zhang, S-X (2013) Investigation of multilingual deep neural networks for spoken term detection. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013, -- to -- pp. 138-143..

Maia, R and Akamine, M and Gales, MJF (2013) Complex cepstrum analysis based on the minimum mean squared error. In: UNSPECIFIED pp. 7972-7976..

Van Dalen, RC and Ragni, A and Gales, MJF (2013) Efficient decoding with generative score-spaces using the expectation semiring. In: UNSPECIFIED pp. 7619-7623..

Chen, L and Gales, MJF and Braunschweiler, N and Akamine, M and Knill, K (2013) Integrated automatic expression prediction and speech synthesis from text. In: UNSPECIFIED pp. 7977-7981..

Zhang, SX and Gales, MJF (2013) Kernelized log linear models for continuous speech recognition. In: UNSPECIFIED pp. 6950-6954..

Latorre, J and Gales, MJF and Knill, K and Akamine, M (2013) Training a supra-segmental parametric F0 model without interpolating F0. In: UNSPECIFIED pp. 6880-6884..

Lanchantin, P and Bell, PJ and Gales, MJF and Hain, T and Liu, X and Long, Y and Quinnell, J and Renals, S and Saz, O and Seigel, MS and Swietojanski, P and Woodland, PC (2013) Automatic transcription of multi-genre media archives. In: UNSPECIFIED pp. 26-31..

Liu, X and Gales, MJF and Woodland, PC (2013) Cross-domain paraphrasing for improving language modelling using out-of-domain data. In: UNSPECIFIED pp. 3424-3428..

Maia, R and Gales, MJF and Stylianou, Y and Akamine, M (2013) Minimum mean squared error based warped complex cepstrum analysis for statistical parametric speech synthesis. In: UNSPECIFIED pp. 2336-2340..

Wan, V and Anderson, R and Blokland, A and Braunschweiler, N and Chen, L and Kolluru, BK and Latorre, J and Maia, R and Stenger, B and Yanagisawa, K and Stylianou, Y and Akamine, M and Gales, MJF and Cipolla, R (2013) Photo-realistic expressive text to talking head synthesis. In: UNSPECIFIED pp. 2667-2669..

Wang, YQ and Gales, MJF (2013) An explicit independence constraint for factorised adaptation in speech recognition. In: UNSPECIFIED pp. 1233-1237..

Liu, X and Gales, MJF and Woodland, PC (2013) Cross-domain Paraphrasing For Improving Language Modelling Using Out-of-domain Data. In: UNSPECIFIED pp. 3391-3395..

Wang, Y-Q and Gales, MJF (2013) An Explicit Independence Constraint for Factorised Adaptation in Speech Recognition. In: UNSPECIFIED pp. 1232-1236..

Long, Y and Gales, MJF and Lanchantin, P and Liu, X and Seigel, MS and Woodland, PC (2013) Improving Lightly Supervised Training for Broadcast Transcription. In: UNSPECIFIED pp. 2186-2190..

Maia, R and Gales, MJF and Stylianou, Y and Akamine, M (2013) Minimum mean squared error based warped complex cepstrum analysis for statistical parametric speech synthesis. In: UNSPECIFIED pp. 2335-2339..

Wan, V and Anderson, R and Blokland, A and Braunschweiler, N and Chen, L and Kolluru, B and Latorre, J and Maia, R and Stenger, B and Yanagisawa, K and Stylianou, Y and Akamine, M and Gales, MJF and Cipolla, R (2013) Photo-Realistic Expressive Text to Talking Head Synthesis. In: UNSPECIFIED pp. 2666-2668..

Roupakia, Z and Ragni, A and Gales, M (2012) Rapid nonlinear speaker adaptation for large-vocabulary continuous speech recognition. In: UNSPECIFIED pp. 1782-1785..

Maia, R and Akamine, M and Gales, MJF and IEEE, (2012) COMPLEX CEPSTRUM AS PHASE INFORMATION IN STATISTICAL PARAMETRIC SPEECH SYNTHESIS. In: UNSPECIFIED pp. 4581-4584..

Wan, V and Latorre, J and Chin, KK and Chen, L and Gales, MJF and Zen, H and Knill, K and Akamine, M and Association, ISC (2012) Combining multiple high quality corpora for improving HMM-TTS. In: UNSPECIFIED pp. 1134-1137..

Chen, L and Gales, MJF and Wan, V and Latorre, J and Akamine, M and Association, ISC (2012) Exploring Rich Expressive Information from Audiobook Data Using Cluster Adaptive Training. In: UNSPECIFIED pp. 958-961..

Ragni, A and Gales, MJF and IEEE, (2012) INFERENCE ALGORITHMS FOR GENERATIVE SCORE-SPACES. In: UNSPECIFIED pp. 4149-4152..

Wang, Y-Q and Gales, MJF and Association, ISC (2012) Model-based approaches to adaptive training in reverberant environments. In: UNSPECIFIED pp. 1194-1197..

Latorre, J and Wan, V and Gales, MJF and Chen, L and Chin, KK and Knill, K and Akamine, M and Association, ISC (2012) Speech factorization for HMM-TTS based on cluster adaptive training. In: UNSPECIFIED pp. 970-973..

Eyben, F and Buchholz, S and Braunschweiler, N and Latorre, J and Wan, V and Gales, MJF and Knill, K and IEEE, (2012) UNSUPERVISED CLUSTERING OF EMOTION AND VOICE STYLES FOR EXPRESSIVE TTS. In: UNSPECIFIED pp. 4009-4012..

Pilkington, NCV and Zen, H and Gales, MJF (2011) Gaussian process experts for voice conversion. In: UNSPECIFIED pp. 2761-2764..

Maia, R and Zen, H and Knill, K and Gales, MJF and Buchholz, S (2011) Multipulse sequences for residual signal modeling. In: UNSPECIFIED pp. 1833-1836..

Zhang, SX and Gales, MJF (2011) Structured support vector machines for noise robust continuous speech recognition. In: UNSPECIFIED pp. 989-992..

Pilkington, NCV and Zen, H and Gales, MJF and Assoc, ISC (2011) Gaussian Process Experts for Voice Conversion. In: UNSPECIFIED 2772-+..

Li, T and Woodland, PC and Diehl, F and Gales, MJF and Assoc, ISC (2011) Graphone Model Interpolation and Arabic Pronunciation Generation. In: UNSPECIFIED pp. 2320-2323..

Liu, X and Gales, MJF and Woodland, PC and Assoc, ISC (2011) Improving LVCSR System Combination Using Neural Network Language Model Cross Adaptation. In: UNSPECIFIED pp. 2868-2871..

Breslin, C and Chin, KK and Gales, MJF and Knill, K and Assoc, ISC (2011) Integrated Online Speaker Clustering and Adaptation. In: UNSPECIFIED pp. 1092-1095..

Maia, R and Zen, H and Knill, K and Gales, MJF and Buchholz, S and Assoc, ISC (2011) Multipulse Sequences for Residual Signal Modeling. In: UNSPECIFIED pp. 1844-1847..

Zhang, S-X and Gales, MJF and Assoc, ISC (2011) Structured Support Vector Machines for Noise Robust Continuous Speech Recognition. In: UNSPECIFIED pp. 996-999..

Diehl, F and Gales, MJF and Liu, X and Tomalin, M and Woodland, PC and Assoc, ISC (2011) Word Boundary Modelling and Full Covariance Gaussians for Arabic Speech-to-Text Systems. In: UNSPECIFIED pp. 784-787..

van Dalen, RC and Gales, MJF (2010) Asymptotically exact noise-corrupted speech likelihoods. In: International Conference on Spoken Language Processing, Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 709-712..

Gales, MJF and Yu, K (2010) Canonical state models for automatic speech recognition. In: International Conference on Spoken Language Processing, Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 58-61..

Park, J and Liu, X and Gales, MJF and Woodland, PC (2010) Improved neural network based language modelling and adaptation. In: International Conference on Spoken Language Processing, Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 1041-1044..

Liu, X and Gales, MJF and Woodland, PC (2010) Language model cross adaptation for LVCSR system combination. In: International Conference on Spoken Language Processing, Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 342-345..

Braunschweiler, N and Gales, MJF and Buchholz, S (2010) Lightly supervised recognition for automatic alignment of large coherent speech recordings. In: International Conference on Spoken Language Processing, Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 2222-2225..

Breslin, C and Chin, KK and Gales, MJF and Knill, K and Xu, H (2010) Prior information for rapid speaker adaptation. In: International Conference on Spoken Language Processing , Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 1644-1647..

Latorre, J and Gales, MJF and Zen, H (2010) Training a parametric-based logF0 model with the minimum generation error criterion. In: International Conference on Spoken Language Processing, Interspeech 2010, 2010-9-26 to 2010-9-30, Makuhari, Japan pp. 2174-2177..

Maia, R and Zen, H and Gales, MJF (2010) Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters. In: 7th ISCA Speech Synthesis Workshop, 2010-9-22 to 2010-9-24, Kyoto, Japan.

Maia, R and Zen, H and Gales, MJF (2010) Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters. In: 7th ICSA Tutorial and Research Workshop on Speech Synthesis, 2010-9-22 to 2010-9-24, Kyoto, Japan.

Liu, X and Gales, MJF and Hieronymus, JL and Woodland, PC (2010) Language model combination and adaptation using weighted finite state transducers. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2010-3-14 to 2010-3-19, Dallas, Texas, USA pp. 5390-5393..

Tomalin, M and Park, J and Diehl, F and Gales, MJF and Woodland, PC (2010) Recent improvements to the Cambridge Arabic speech-to-text systems. In: IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2010-3-14 to 2010-3-19, Dallas, Texas pp. 4382-4385..

Zen, H and Gales, MJF and Nankaku, Y and Tokuda, K (2010) Statistical parametric synthesis based on products of experts. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2010-3-14 to 2010-3-19, Dallas, Texas, USA pp. 4242-4245..

Flego, F and Gales, MJF (2010) Discriminative adaptive training with VTS and JUD. In: 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, 2010-12-13 to 2010-12-17, Merano, Italy pp. 170-175..

Xu, H and Gales, MJF and Chin, KK (2010) Improving joint uncertainty decoding performance by predictive methods for noise robust speech recognition. In: 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, 2010-12-13 to 2010-12-17, Merano, Italy pp. 222-227..

Gales, MJF and Ragni, A and AlDamarki, H and Gautier, C (2010) Support vector machines for noise robust ASR. In: 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, 2010-12-13 to 2010-12-17, Merano, Italy pp. 205-210..

Liu, X and Gales, MJF and Woodland, PC (2010) Language model cross adaptation for LVCSR system combination. In: UNSPECIFIED pp. 342-345..

Park, J and Liu, X and Gales, MJF and Woodland, PC (2010) Improved Neural Network Based Language Modelling and Adaptation. In: UNSPECIFIED pp. 1041-1044..

Kim, D and Gales, MJF (2009) Adaptive training with noisy constrained maximum likelihood linear regression for noise robust speech recognition. In: 10th Annual Conference of the International Speech Communication Association, 2009-9-6 to 2009-9-10, Brighton, UK pp. 2383-2386..

Park, J and Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2009) Efficient generation and use of MLP features for Arabic speech recognition. In: Interspeech 2009, 10th International Conference of the International Speech Communication Association, 2009-9-6 to 2009-9-10, Brighton, UK pp. 236-239..

Hieronymus, JL and Liu, X and Gales, MJF and Woodland, PC (2009) Exploiting Chinese character models to improve speech recognition performance. In: Interspeech 2009, 10th International Conference of the International Speech Communication Association, 2009-9-6 to 2009-9-10, Brighton, UK pp. 364-367..

Flego, F and Gales, MJF (2009) Incremental adaptation with VTS and joint adaptively trained systems. In: Interspeech 2009, 10th Annual Conference of the International Speech Communication Association, 2009-9-6 to 2009-9-10, Brighton, UK pp. 1251-1254..

Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2009) Morphological analysis and decomposition for Arabic speech-to-text systems. In: 10th International Conference of the International Speech Communication Association, Interspeech 2009, 2009-9-6 to 2009-9-10, Brighton, UK pp. 2675-2678..

van Dalen, RC and Gales, MJF (2009) Transforming features to compensate speech recogniser models for noise. In: 10th International Conference of the International Speech Communication Association, Interspeech 2009, 2009-9-6 to 2009-9-10, Brighton, UK pp. 2499-2502..

Liu, X and Gales, MJF and Woodland, PC (2009) Use of contexts in language model interpolation and adaptation. In: Interspeech 2009, 10th International Conference of the International Speech Communication Association, 2009-9-6 to 2009-9-10, Brighton, UK pp. 360-363..

Longworth, C and van Dalen, RC and Gales, MJF (2009) Variational dynamic kernels for speaker verification. In: 10th International Conference of the International Speech Communication Association, Interspeech 2009, 2009-9-6 to 2009-9-10, Brighton, UK pp. 1571-1574..

Raut, CK and Gales, MJF (2009) Bayesian discriminative adaptation for speech recognition. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP 2009, 2009-4-19 to 2009-4-24, Taipei, Taiwan pp. 4361-4364..

van Dalen, RC and Gales, MJF (2009) Extended VTS for noise-robust speech recognition. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP 2009, 2009-4-19 to 2009-4-24, Taipei, Taiwan pp. 3829-3832..

van Dalen, RC and Gales, MJF (2009) Extended VTS for noise-robust speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, ICASSP 2009., 2009-4-19 to 2009-4-24, Taipei, Taiwan pp. 3829-3832..

Flego, F and Gales, MJF (2009) Incremental predictive and adaptive noise compensation. In: IEEE Conference on Acoustics Speech and Signal Processing, ICASSP 2009, 2009-4-19 to 2009-4-24, Taipei, Taiwan pp. 3837-3840..

Park, J and Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2009) Training and adapting MLP features for Arabic speech recognition. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP 2009, 2009-4-19 to 2009-4-24, Taipei, Taiwan pp. 4461-4464..

Gales, MJF and Flego, F (2009) Combining VTS model compensation and support vector machines. In: 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2009, 2009-4-17 to 2009-4-20, Taipei, Taiwan pp. 3821-3824..

Gales, MJF (2009) Acoustic Modelling for Speech Recognition: Hidden Markov Models and Beyond? In: UNSPECIFIED p. 44..

Kim, DK and Gales, MJF (2009) Adaptive Training with Noisy Constrained Maximum Likelihood Linear Regression for Noise Robust Speech Recognition. In: UNSPECIFIED pp. 2367-2370..

Park, J and Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2009) Efficient Generation and Use of MLP Features for Arabic Speech Recognition. In: UNSPECIFIED pp. 240-243..

Flego, F and Gales, MJF (2009) Incremental Adaptation with VTS and Joint Adaptively Trained Systems. In: UNSPECIFIED pp. 1247-1250..

Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2009) Morphological Analysis and Decomposition for Arabic Speech-to-Text Systems. In: UNSPECIFIED pp. 2631-2634..

van Dalen, RC and Flego, F and Gales, MJF (2009) Transforming Features to Compensate Speech Recogniser Models for Noise. In: UNSPECIFIED pp. 2459-2462..

Liu, X and Gales, MJF and Woodland, PC (2009) Use of Contexts in Language Model Interpolation and Adaptation. In: UNSPECIFIED pp. 360-363..

Longworth, C and van Dalen, RC and Gales, MJF (2009) Variational Dynamic Kernels for Speaker Verification. In: UNSPECIFIED pp. 1523-1526..

Raut, CK and Yu, K and Gales, MJF (2008) Adaptive training using discriminative mapping transforms. In: 9th Annual Conference of the International Speech Communication Association (Interspeech 2008) incorporating the 12th Australasian International Conference on Speech Science and Technology, SST' 08, 2008-9-22 to 2008-9-26, Brisbane, Australia pp. 22-26..

Liu, XA and Gales, MJF and Woodland, PC (2008) Context dependent language model adaptation. In: 9th Annual Conference of the International Speech Communication Association (Interspeech 2008) incorporating the 12th Australasian International Conference on Speech Science and Technology, SST' 08, 2008-9-22 to 2008-9-26, Brisbane, Australia.

van Dalen, RC and Gales, MJF (2008) Covariance modelling for noise-robust speech recognition. In: 9th Annual Conference of the International Speech Communication Association (Interspeech 2008) incorporating the 12th Australasian International Conference on Speech Science and Technology, SST' 08, 2008-9-22 to 2008-9-26, Brisbane, Australia.

Gales, MJF and Longworth, C (2008) Discriminative classifiers with generative kernels for noise-robust ASR. In: 9th Annual Conference of the International Speech Communication Association (Interspeech 2008) incorporating the 12th Australasian International Conference on Speech Science and Technology, SST' 08, 2008-9-22 to 2008-9-26, Brisbane, Australia.

Longworth, C and Gales, MJF (2008) A generalised derivative kernel for speaker verification. In: 9th Annual Conference of the International Speech Communication Association (Interspeech 2008) incorporating the 12th Australasian International Conference on Speech Science and Technology, SST' 08, 2008-9-22 to 2008-9-26, Brisbane, Australia.

Longworth, C and Gales, MJF (2008) Multiple kernel learning for speaker verification. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP' 08, 2008-3-31 to 2008-4-4, Las Vegas, USA pp. 1581-1584..

Diehl, F and Gales, MJF and Tomalin, M and Woodland, PC (2008) Phonetic pronunciations for arabic speech-to-text systems. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP' 08, 2008-3-31 to 2008-4-4, Las Vegas, USA pp. 1573-1576..

Yu, K and Gales, MJF and Woodland, PC (2008) Unsupervised discriminative adaptation using discriminative mapping transforms. In: International Conference on Acoustics, Speech and Signal Processing, ICASSP 2008, 2008-3-30 to 2008-4-4, Las Vegas, USA pp. 4273-4276..

Raut, CK and Yu, K and Gales, MJF (2008) Adaptive training using discriminative mapping transforms. In: UNSPECIFIED pp. 1697-1700..

Raut, CK and Yu, K and Gales, MJF (2008) Adaptive Training using Discriminative Mapping Transforms. In: UNSPECIFIED pp. 1697-1700..

Liu, X and Gales, MJF and Woodland, PC (2008) Context Dependent Language Model Adaptation. In: UNSPECIFIED pp. 837-840..

van Dalen, RC and Gales, MJF (2008) Covariance Modelling for Noise-Robust Speech Recognition. In: UNSPECIFIED pp. 2000-2003..

Gales, MJF and Longworth, C (2008) Discriminative Classifiers with Generative Kernels for Noise Robust ASR. In: UNSPECIFIED pp. 1996-1999..

Longworth, C and Gales, MJF (2008) A Generalised Derivative Kernel for Speaker Verification. In: UNSPECIFIED pp. 1381-1384..

Gales, MJF and Liu, X and Sinha, R and Woodland, PC and Yu, K and Matsoukas, S and Ng, T and Nguyen, K and Nguyen, L and Gauvain, JL and Lamel, L and Messaoudi, A (2007) Speech recognition system combination for machine translation. In: UNSPECIFIED.

Wang, L and Gales, MJF and Woodland, PC (2007) Unsupervised training for mandarin broadcast news and conversation transcription. In: UNSPECIFIED.

Breslin, C and Gales, MJF (2007) Building multiple complementary systems using directed decision trees. In: Interspeech 2007, 2007-8-27 to 2007-8-31, Antwerp, Belgium.

Longworth, C and Gales, MJF (2007) Parametric and derivative kernels for speaker verification. In: Interspeech 2007, 2007-8-27 to 2007-8-31, Antwerp, Belgium.

Yu, K and Gales, MJF and Woodland, PC (2007) Unsupervised training using directed manual transcription for recognising Mandarin broadcast audio. In: Interspeech 2007, 2007-8-27 to 2007-8-31, Antwerp, Belgium.

Liao, H and Gales, MJF (2007) Adaptive training with joint uncertainty decoding for robust recognition of noisy data. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP' 07, 2007-4-15 to 2007-4-20, Honolulu, HI, US pp. 389-392..

Breslin, C and Gales, MJF (2007) Complementary system generation using directed decision trees. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP' 07, 2007-4-15 to 2007-4-20, Honolulu, HI, US pp. 337-340..

Sim, KC and Byrne, WJ and Gales, MJF and Sahbi, H and Woodland, PC (2007) Consensus network decoding for statistical machine translation system combination. In: The IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP'07, 2007-4-15 to 2007-4-20, Honolulu, HI, US pp. 105-108..

Tomalin, M and Gales, MJF and Liu, XA and Sinha, KC and Wang, L and Woodland, PC and Yu, K (2007) Improving speech transcription for Mandarin-English translation. In: IEEE International Conference on Acoustics Speech and Signal Processing 2007 (ICASSP 2007), 2007-4-15 to 2007-4-20, Honolulu, HI, US pp. 97-100..

Gales, MJF and Liu, X and Sinha, R and Woodland, PC and Yu, K and Matsoukas, S and Ng, T and Nguyen, K and Nguyen, L and Gauvain, JL and Lamel, L and Messaoudi, A (2007) Speech recognition system combination for machine translation. In: IEEE International Conference on Acoustics Speech and Signal Processing 2007 (ICASSP 2007), 2007-4-15 to 2007-4-20, Honolulu, HI, US pp. 1277-1280..

Wang, L and Gales, MJF and Woodland, PC (2007) Unsupervised training for Mandarin broadcast news and conversation transcription. In: IEEE International Conference on Acoustics Speech and Signal Processing 200, ICASSP' 07, 2007-4-15 to 2007-4-20, Honolulu, HI, US pp. 353-356..

Gales, MJF (2007) Discriminative models for speech recognition. In: Information Theory and Applications Workshop, 2007-1-29 to 2007-2-2, La Jolla,CA, US pp. 170-176..

Gales, MJF and Diehl, F and Raut, CK and Tomalin, M and Woodland, PC and Yu, K (2007) Development of a phonetic system for large vocabulary Arabic speech recognition. In: 2007 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2007), 2007-12-9 to 2007-12-13, Kyoto, Japan.

Liu, XA and Byrne, WJ and Gales, MJF and de Gispert, A and Tomalin, M and Woodland, PC and Yu, K (2007) Discriminative language model adaptation for Mandarin broadcast speech transcription and translation. In: 2007 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2007), 2007-12-9 to 2007-12-13, Kyoto, Japan pp. 153-158..

Gales, MJF and van Dalen, RC (2007) Predictive linear transforms for noise robust speech recognition. In: 2007 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU2007), 2007-12-9 to 2007-12-13, Kyoto, Japan.

Liu, XA and Byrne, WJ and Gales, MJF and De Gispert, A and Tomalin, M and Woodland, PC and Yu, K (2007) Discriminative language model adaptation for Mandarin broadcast speech transcription and translation. In: UNSPECIFIED pp. 153-158..

Breslin, C and Gales, MJF (2007) Building Multiple Complementary Systems using Directed Decision Trees. In: UNSPECIFIED pp. 793-796..

Longworth, C and Gales, MJF (2007) Derivative and Parametric Kernels for Speaker Verification. In: UNSPECIFIED pp. 849-852..

Gales, MJF and Diehl, F and Raut, CK and Tomalin, M and Woodland, PC and Yu, K (2007) Development of a phonetic system for large vocabulary Arabic speech recognition. In: UNSPECIFIED pp. 24-29..

Gales, MJF (2007) Discriminative-models for speech recognition. In: UNSPECIFIED pp. 168-174..

Tomalin, M and Gales, MJF and Liu, XA and Sim, KC and Sinha, R and Wang, L and Woodland, PC and Yu, K (2007) Improving speech transcription for Mandarin-English translation. In: UNSPECIFIED pp. 97-100..

Gales, MJF and van Dalen, RC (2007) Predictive linear transforms for noise robust speech recognition. In: UNSPECIFIED pp. 59-64..

Yu, K and Gales, MJF and Woodland, PC (2007) Unsupervised Training with Directed Manual Transcription for Recognising Mandarin Broadcast Audio. In: UNSPECIFIED pp. 2896-2899..

Longworth, C and Gales, MJF (2006) Discriminative adaptation for speaker verification. In: InterSpeech 2006, 2006-9-17 to 2006-9-21, Pittsburgh, PA, US.

Breslin, C and Gales, MJF (2006) Generating complementary systems for speech recognition. In: 9th International Conference on Spoken Language Processing (ICSLP) (InterSpeech 2006), 2006-9-17 to 2006-9-21, Pittsburgh, PA, US pp. 525-528..

Liao, H and Gales, MJF (2006) Issue with uncertainty decoding for noise robust speech recognition. In: 9th International Conference on Spoken Language Processing (ICSLP), 2006-9-17 to 2006-9-21, Pittsburgh, PA, US.

Layton, MI and Gales, MJF (2006) Augmented statistical models for speech recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2006-5-14 to 2006-5-19, Toulouse, France.

Sinha, R and Gales, MJF and Kim, DY and Liu, X and Sim, KC and Woodland, PC (2006) The CU-HTK Mandarin broadcast news transcription system. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP'06, 2006-5-14 to 2006-5-19, Toulouse, France pp. 1077-1080..

Yu, K and Gales, MJF (2006) Incremental adaptation using Bayesian inference. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2006), 2006-5-14 to 2006-5-19, Toulouse, France.

Layton, MI and Gales, MJF (2006) Augmented statistical models for speech recognition. In: UNSPECIFIED pp. 129-132..

Longworth, C and Gales, MJF (2006) Discriminative Adaptation for Speaker Verification. In: UNSPECIFIED pp. 1467-1470..

Yu, K and Gales, MJF (2006) Incremental adaptation using Bayesian inference. In: UNSPECIFIED pp. 217-220..

Liao, H and Gales, MJF (2006) Issues with Uncertainty Decoding for Noise Robust Speech Recognition. In: UNSPECIFIED pp. 1121-1124..

Layton, M and Gales, MJF (2005) Acoustic modelling using continuous rational kernels. In: Machine Learning for Signal Processing Workshop, 2005-9-28 to 2005-9-30, Mystic, CT, US.

Sim, KC and Gales, MJF (2005) Adaptation of precision matrix models on large vocabulary continuous speech recognition. In: The IEEE International Conference on Acoustics, Speech and Signal Processing, 2005-3- to --, Philadelphia, PA, US pp. 97-100..

Layton, M and Gales, MJF (2005) Augmented statistical models: exploiting generative models in discriminative classifiers. In: 19th Annual Conference on Neural Information Processing Systems (NIPS Workshop), 2005-12-9 to --, Whistler, Canada.

Liao, H and Gales, MJF (2005) Joint uncertainty decoding for noise robust speech recognition. In: The 9th European Conference on Speech Communciation and Technology (EuroSpeech), 2005-- to --, Lisbon, Portugal pp. 3129-3132..

Sim, KC and Gales, MJF (2005) Temporally varying model parameters for large vocabulary continuous speech recognition. In: The 9th European Conference on Speech Communciation and Technology (EuroSpeech), 2005-- to --, Lisbon, Portugal pp. 2137-2140..

Liu, X and Gales, MJF and Sim, KC and Yu, K (2005) Investigation of acoustic modeling techniques for LVCSR systems. In: The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 05), -- to --.

Evermann, G and Chan, HY and Gales, MJF and Jia, B and Mrva, D and Woodland, PC and Yu, K (2005) Development of the CU-HTK 2004 broadcast news transcription systems. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP '05, 2005-3-19 to 2005-3-23, Philadelphia, PA, US pp. 861-864..

Gales, MJF and Jia, B and Liu, X and Sim, KC and Woodland, PC and Yu, K (2005) Development of the CUHTK 2004 Mandarin conversational telephone speech transcription system. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP '05, 2005-3-19 to 2005-3-23, Philadelphia, PA, USA pp. 841-844..

Liu, X and Gales, MJF and Sim, KC and Yu, K (2005) Investigation of acoustic modeling techniques for LVCSR systems. In: The IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 05), 2005-3-18 to 2005-3-23, Philadelphia, PA, US pp. 849-852..

Evermann, G and Chan, HY and Gales, MJF and Jia, B and Mrva, D and Woodland, PC and Yu, K (2005) Training LVCSR systems on thousands of hours of data. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP '05, 2005-3-19 to 2005-3-23, Philadelphia, PA, US pp. 209-212..

Yu, K and Gales, MJF (2005) Bayesian adaptation and adaptively trained systems. In: 2005 IEEE Workshop on Automatic Speech Recognition and Understanding, 2005-11-28 to 2005-12-1, San Juan, PR, US pp. 209-214..

Gales, MJF and Jia, B and Liu, X and Sim, KC and Woodland, PC and Yu, K (2005) Development of the CUHTK 2004 Mandarin conversational telephone speech transcription system. In: UNSPECIFIED.

Layton, MI and Gales, MJF (2005) Acoustic modelling using continuous rational kernels. In: UNSPECIFIED pp. 165-170..

Evermann, G and Chan, HY and Gales, MJF and Hain, T and Liu, X and Mrva, D and Wang, L and Woodland, PC (2004) Development of the 2003 CU-HTK conversational telephone speech transcription system. In: UNSPECIFIED.

Liu, X and Gales, MJF (2004) Automatic model complexity control and compression using discriminative growth functions. In: The 29th IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), 2004-5- to --, Montreal, Quebec, Canada pp. 797-800..

Sim, KC and Gales, MJF (2004) Basis superposition precision matrix modeling for large vocabulary continuous speech recognition. In: The 29th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2004-5- to --, Montreal, Quebec, Canada pp. 801-804..

Evermann, G and Chan, HY and Gales, MJF and Jia, B and Liu, X and Mrva, D and Sim, KC and Wang, L and Woodland, PC (2004) Development of the 2004 CU-HTK English CTS systems using more than two thousand hours of data. In: DARPA RT 2004 (Rich Transcription), 2004-11- to --, Palisades, NY, US.

Gales, MJF and Jia, B and Liu, X and Sim, KC and Woodland, PC and Yu, K (2004) Development of the CUHTK 2004 RT04F Mandarin conversational telephone speech transcription system. In: DARPA RT 2004 (Rich Transcription), 2004-11- to --, Palisades, NY, USA.

Rosti, AVI and Gales, MJF (2004) Rao-blackwellised gibbs sampling for switching linear dynamical systems. In: The 29th IEEE International conference on Acoustics, Speech and Signal Processing (ICASSP), 2004-5- to --, Montreal, Quebec, Canada pp. 809-812..

Kim, DY and Chan, HY and Evermann, G and Gales, MJF and Mrva, D and Sim, KC and Woodland, PC (2004) Recent developments at Cambridge in broadcast news transcription. In: DARPA RT 2004 (Rich Transcription), 2004-11- to --, Palisades, NY, US.

Tranter, SE and Gales, MJF and Sinha, R and Umesh, S and Woodland, PC (2004) The development of the Cambridge University RT-04 diarisation system. In: DARPA RT 2004 (Rich Transcription), 2004-11- to --, Palisades, NY, US.

Liu, X and Gales, MJF (2004) Automatic model complexity control and compression using discriminative growth functions. In: The 29th IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), -- to --.

Yu, K and Gales, MJF (2004) Adaptive training using structured transforms. In: The 29th IEEE International Conference on Acoustics, Speech and Signal Proceedings (ICASSP 04), 2004-5-17 to 2004-5-21, Montreal, Quebec, Canada pp. 317-320..

Evermann, G and Chan, HY and Gales, MJF and Hain, T and Liu, X and Mrva, D and Wang, L and Woodland, PC (2004) Development of the 2003 CU-HTK conversational telephone speech transcription system. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP'04, 2004-5-17 to 2004-5-21, Montreal, Quebec, Canada pp. 249-252..

Kim, DY and Gales, MJF and Hain, T and Woodland, PC (2004) Using VTLN for broadcast news transcription. In: 8th International Conference on Spoken Language Processing, 2004-10-4 to 2004-10-8, Jeju Island, Korea pp. 1953-1956..

Liu, X and Gales, MJF (2003) Automatic model complexity control using marginalized discriminative growth functions. In: The IEEE Workshop on Automatic Speech Recognition and Understanding, 2003-11- to --, St Thomas, VI, US pp. 37-42..

Airey, SS and Gales, MJF (2003) Product of Gaussians and multiple stream systems. In: The 28th IEEE International Conference on Acoustics Speech and Signal Processing, 2003-4- to --, Hong Kong, China pp. 892-895..

Airey, SS and Gales, MJF (2003) Product of Gaussians as a distributed representation for speech recognition. In: Proceedings of Eurospeech, 2003-9- to --, Geneva, Switzerland pp. 877-880..

Liu, X and Gales, MJF and Woodland, PC (2003) Automatic complexity control for HLDA systems. In: IEEE International Conference on Acoustics Speech and Signal Processing, 2003-4-6 to 2003-4-10, Hong Kong, China pp. 132-135..

Povey, D and Woodland, PC and Gales, MJF (2003) Discriminative map for acoustic model adaptation. In: IEEE International Conference on Acoustics Speech and Signal Processing, 2003-4-6 to 2003-4-10, Hong Kong, China pp. 312-315..

Gales, MJF and Dong, Y and Povey, D and Woodland, PC (2003) Porting: SwitchBoard to the VoiceMail task. In: IEEE International Conference on Acoustics Speech and Signal Processing, 2003-4-6 to 2003-4-10, Hong Kong, China pp. 536-539..

Airey, SS and Gales, MJF (2003) Product of Gaussians and multiple stream systems. In: UNSPECIFIED pp. 844-847..

Stuttle, MN and Gales, MJF (2002) Combining a Gaussian mixture model front end with MFCC parameters. In: The 7th International Conference on Spoken Language Processing (Interspeech), 2002-9- to --, Denver, CO, US pp. 1565-1568..

Rosti, AVI and Gales, MJF (2002) Factor analysed HMMs (Hidden Markov Models). In: The 26th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2001-5- to --, Salt Lake City, UT, US pp. 949-952..

Gales, MJF (2002) The HMM error model. In: The 26th International Conference on Acoustics, Speech, and Signal Processing, 2001-5- to --, Salt Lake City, UT, US pp. 937-940..

Cordoba, R and Woodland, PC and Gales, MJF (2002) Improved cross-task recognition using MMIE training. In: IEEE International Conference on Acoustics Speech and Signal Processing, 2001-5- to --, Salt Lake City, UT, US pp. 85-88..

Smith, ND and Gales, MJF (2002) SVMs for speech recognition. In: The 26th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2001-5- to --, Salt Lake City, UT, US pp. 77-80..

Smith, ND and Gales, MJF (2002) Using SVMs and discriminative models for speech recognition. In: UNSPECIFIED pp. 77-80..

Gales, MJF (2001) Acoustic factorisation. In: The IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2001), 2001-12- to --, Madonna di Campiglio, Italy pp. 77-80..

Gales, MJF (2001) Adaptive training for robust ASR. In: The IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU 2001), 2001-12- to --, Madonna di Campiglio, Italy pp. 15-20..

Gales, MJF (2001) Multiple-cluster adaptive training schemes. In: 26th International Conference on Acoustics, Speech, and Signal Processing, 2001-5- to --, Salt Lake City, UT, US pp. 361-364..

Smith, N and Gales, MJF (2001) Speech recognition using SVMs. In: The 15th Conference on Neural Information Processing Systems, 2001-12- to --, British Columbia, Canada pp. 1197-1204..

Stuttle, MN and Gales, MJF (2001) A mixture of gaussians front end for speech recognition. In: The 7th European Conference on Speech Communication and Technology, 2001-9- to --, Aalborg, Denmark pp. 675-678..

Aiyer, A and Gales, MJF and Picheny, MA (2000) Rapid likelihood calculation of subspace clustered Gaussian components. In: The IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2000), 2000-6- to --, Istanbul, Turkey pp. 1519-1522..

Eide, E and Maison, B and Kavensky, D and Olsen, P and Chen, S and Mangu, L and Gales, MJF and Novak, M and Gopinath, R (2000) IBM's 10xReal-time broadcast news transciption used in the 1999 hub4 evaluation. In: Speech Transcription Workshop, 2000-5-16 to 2000-5-19, Maryland, MD, US.

Eide, E and Maison, B and Kavensky, D and Olsen, P and Chen, S and Mangu, L and Gales, MJF (2000) Transcription of broadcast news with time constraint: IBM's 10xRT hub4 system. In: 6th International Conference of Spoken Language Processing (Interspeech 2000), 2000-10-16 to 2000-10-20, Beijing, China.

Gales, MJF and Olsen, PA (1999) Tail distribution modelling using the richter and power exponential distributions. In: 6th European Conference on Speech Communication and Technology (Eurospeech), 1999-9-5 to 1999-9-9, Budapest, Hungary -..

Chen, S and Eide, EM and Gales, MJF and Gopinath, RA and Kavensky, D and Olsen, PA (1999) Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news. In: DARPA Broadcast News Workshop, 1999-2-28 to 1999-3-3, Herndon, VA, US.

Chen, S and Eide, EM and Gales, MJF and Gopinath, RA and Kavensky, RA (1999) Recent improvements to IBM's speech recognition system for automatic transcription of broadcast news. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP'99, 1999-3-21 to 1999-3-24, Phoenix, AZ, US pp. 37-40..

Gales, MJF (1998) Cluster adaptive training for speech recognition. In: 5th International Conference on Spoken Language Processing, -- to --.

Gales, MJF (1998) Semi-tied covariance matrices. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing 1998, 1998-5- to --, Seattle, WA, US pp. 657-660..

Chen, S and Gales, MJF and Gopalakrishnan, PS and Gopinath, RA and Kavensky, D and Olsen, P and Polymenakos, L (1998) IBM's LVCSR system for transcription of broadcast news used in the 1997 hub4 english evaluation. In: DARPA Broadcast News Transcription and Understanding Workshop, 1998-2-8 to 1998-2-11, Lansdowne, VA, US.

Gales, MJF (1997) Transformation smoothing for speaker and environmental adaptation. In: 5th European Conference on Speech Communication and Technology (Eurospeech), 1997-9-22 to 1997-9-25, Rhodes, Greece.

Nock, H and Gales, MJF and Young, SJ (1997) A comparative study of methods for phonetic decision-tree state clustering. In: 5th European Conference on Speech Communication and Technology (Eurospeech 1997), 1997-9-22 to 1997-9-25, Rhodes, Greece.

Woodland, PC and Gales, MJF and Pye, D and Young, SJ (1997) Broadcast news transcription using HTK. In: IEEE International Conference on Acoustics Speech and Signal Processing, ICASSP 97, 1997-4-21 to 1997-4-24, Munich, Germany pp. 719-722..

Knill, K and Gales, MJF and Young, SJ (1996) Use of Gaussian selection in large vocabulary continuous speech recognition using HMMs. In: The 4th International Conference on Spoken Language Processing (ICSLP), 1996-10- to --, Philadelphia, PA, US pp. 470-473..

Woodland, PC and Gales, MJF and Pye, D and Valtchev, V (1996) The HTK large vocabulary recognition system for the 1995 ARPA H3 task. In: ARPA Continuous Speech Recognition Workshop, 1996-2- to --, Harriman, NY, US pp. 99-104..

Woodland, PC and Gales, MJF and Pye, D (1996) Improving environmental robustness in large vocabulary speech recognition. In: IEEE International Conference on Acoustics Speech and Signal Processing, 1996-5-7 to 1996-5-10, Atlanta, GA, US pp. 65-68..

Woodland, PC and Gales, MJF and Pye, D and Young, SJ (1996) The development of the 1996 HTK broadcast news transcription system. In: Proceedings of DARPA Speech Recognition Workshop, 1996-2-18 to 1996-2-21, Arden House, NY, US pp. 73-78..

Woodland, PC and Pye, D and Gales, MJF (1996) Iterative unsupervised adaptation using maximum likelihood linear regression. In: 4th International Conference on Spoken Language Processing, ICSLP 96, 1996-10-3 to 1996-10-6, Philadelphia, PA, US pp. 1133-1136..

Gales, MJF and Pye, D and Woodland, PC (1996) Variance compensation within the MLLR framework for robust speech recognition and speaker adaptation. In: The 4th International Conference on Spoken Language Processing, 1996-10-3 to 1996-10-6, Philadelphia, PA, US pp. 1832-1835..

Gales, MJF and Young, SJ (1995) The application of parallel model combination to a large vocabulary dictation task. In: 4th European Conference on Speech Communication and Technology (EUROSPEECH 95), 1995-9-18 to 1995-9-21, Madrid, Spain pp. 1983-1986..

Gopinath, RA and Gales, MJF and Gopalakrishnan, PS and Balakrishnan Aiyer, S and Picheny, MA (1995) Robust speech recognition in noise --- performance of the IBM continuous speech recogniser on the ARPA noise spoke task. In: Proceedings of ARPA SLT Workshop, 1995-1- to --, Austin, TX, US pp. 127-130..

Knill, K and Gales, MJF and Young, SJ (1995) Video mail retrieval using voice: an overview of the stage 2 system. In: The Final Workshop on Multimedia Information Retrieval (Miro '95), 1995-9- to --, Glasgow, UK 6-..

Gales, MJF and Young, SJ (1995) A fast and flexible implementation of parallel model combination. In: The International Conference on Acoustics, Speech, and Signal Processing (ISCSSP), 1995-5- to --, Detroit, MI, US pp. 133-136..

Gales, MJF and Young, SJ (1993) HMM recognition in noise using parallel model combination. In: 3rd European Conference on Speech Communication and Technology (EUROSPEECH 93), 1993-9-21 to 1993-9-23, Berlin, Germany pp. 837-840..

Gales, MJF and Young, SJ (1993) Segmental hidden Markov models. In: 3rd European Conference on Speech Communication and Technology (EUROSPEECH 93), 1993-9-21 to 1993-9-23, Berlin, Germany pp. 1579-1582..

GALES, MJF and YOUNG, S (1992) AN IMPROVED APPROACH TO THE HIDDEN MARKOV MODEL DECOMPOSITION OF SPEECH AND NOISE. In: UNSPECIFIED A233-A236..

Kyriakopoulos, K and Gales, M and Knill, K Automatic characterisation of the pronunciation of non-native English speakers using phone distance features. In: 7th ISCA Workshop on Speech and Language Technology in Education, 2017-8-25 to 2017-8-26, Djurö, Stockholm, Sweden. (Unpublished)

Ragni, A and Gales, MJF Derivative Kernels for Noise Robust ASR. In: IEEE Workshop on Automatic Speech Recognition and Understanding, 2011-12-11 to 2011-12-15. (Unpublished)

Manakul, P and Gales, MJF Long-Span Summarization via Local Attention and Content Selection. In: UNSPECIFIED. (Unpublished)

Gales, M and Malinin, A Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness. In: NeurIPS, 2019-12-8 to 2019-12-14. (Unpublished)

Malinin, A and Knill, K and Ragni, A and Wang, Y and Gales, M An attention based model for off-topic spontaneous spoken response detection: An Initial Study. In: 7th ISCA Workshop on Speech and Language Technology, 2017-8-25 to 2017-8-26, Djurö, Stockholm, Sweden. (Unpublished)

Monograph

Kim, DK and Gales, MJF (2009) Noisy CMLLR for noise-robust speech recognition. Technical Report. University of Cambridge.

Gales, MJF and Flego, F (2008) Discriminative classifiers and generative kernels for noise robust speech recognition. Technical Report. University of Cambridge, Cambridge, UK.

Liao, H and Gales, MJF (2006) Joint uncertainty decoding for robust large vocabulary speech recognition. Technical Report. University of Cambridge.

Yu, K and Gales, MJF (2004) Discriminative cluster adaptive training. Technical Report. University of Cambridge, Cambridge, UK.

Layton, MI and Gales, MJF (2004) Maximum margin training of generative kernels. Technical Report. University of Cambridge, Cambridge, UK.

Sim, KC and Gales, MJF (2004) Precision matrix modelling for large vocabulary continuous speech recognition. Technical Report. University of Cambridge, Cambridge, UK.

Liao, H and Gales, MJF (2004) Uncertainty decoding for noise robust automatic speech recognition. Technical Report. University of Cambridge.

Hain, T and Woodland, PC and Evermann, G and Gales, MJF and Liu, X and Moore, G and Povey, D and Wang, L (2003) Automatic transcription of conversational telephone speech: development of the CU-HTK 2002 system. Technical Report. Cambridge University Engineering Department, Cambridge, UK.

Rosti, AV and Gales, MJF (2003) Factor analysed hidden Markov models for speech recognition. Technical Report. Cambridge University, Cambridge, UK.

Airey, SS and Gales, MJF (2003) Product of Gaussians for speech recognition. Technical Report. Cambridge University, Cambridge, UK.

Rosti, AV and Gales, MJF (2003) Switching linear dynamical systems for speech recognition. Technical Report. Cambridge University, Cambridge, UK.

Smith, ND and Gales, MJF (2002) Using SVMs to classify variable length speech patterns. Technical Report. Cambridge University, Cambridge, UK.

Smith, ND and Gales, MJF and Niranjan, M (2001) Data-dependent Kernels in SVM classification of speech patterns. Technical Report. Cambridge Univeristy, Cambridge, UK.

Rosti, AV and Gales, MJF (2001) Generalised linear Gaussian models. Technical Report. Cambridge University, Cambridge, UK.

Gales, MJF (2001) Transformation streams and the HMM error model. Technical Report. Cambridge University, Cambridge, UK.

Gales, MJF (1999) Maximum likelihood multiple projection schemes for hidden Markov models. Technical Report. Cambrisge University, Cambridge, UK.

Gales, MJF (1997) Adapting semi-tied full-convariance matrix HMMs. Technical Report. Cambridge University, Cambridge, UK.

Gales, MJF (1997) Maximum likelihood linear transformations for HMM-based speech recognition. Technical Report. Cambridge University, Cambridge, UK.

Gales, MJF (1997) Semi-tied full-covariance matrices for hidden Markov models. Technical Report. Cambridge University, Cambridge, UK.

Gales, MJF and Knill, KM and Young, SJ (1997) State-based Gaussian selection in large vocabulary continuous speech recognition using HMMs. Technical Report. University of Cambridge: Department of Engineering, Cambridge, UK.

Gales, MJF and Woodland, PC (1996) Variance compensation within the MLLR framework. Technical Report. Cambridge University Engineering Department, Cambridge, UK.

Gales, MJF (1996) The generation and use of regression class trees for MLLR adaptation. Technical Report. Cambridge University, Cambridge, UK.

Gales, MJF and Young, SJ (1994) Robust continuous speech recognition using parallel model combination. Technical Report. University of Cambridge: Department of Engineering, Cambridge, UK.

Gales, MJF and Young, SJ (1993) PMC for speech recognition in additive and convolutional noise. Technical Report. University of Cambridge: Department of Engineering, Cambridge, UK.

Gales, MJF and Young, SJ (1993) Parallel model combination for speech recognition in noise. Technical Report. University of Cambridge: Department of Engineering, Cambridge, UK.

Gales, MJF and Young, SJ (1993) The theory of segmental hidden Markov models. Technical Report. University of Cambridge: Department of Engineering, Cambridge, UK.

Thesis

Gales, MJF (1995) Model-based techniques for noise robust speech recognition. PhD thesis, UNSPECIFIED.

This list was generated on Sun Nov 28 04:24:53 2021 GMT.