| The HTK book S Young, G Evermann, M Gales, T Hain, D Kershaw, X Liu, G Moore, ... Cambridge university engineering department 3 (175), 12, 2002 | 7212 | 2002 |
| Maximum likelihood linear transformations for HMM-based speech recognition MJF Gales Computer speech & language 12 (2), 75-98, 1998 | 2061 | 1998 |
| The application of hidden Markov models in speech recognition M Gales, S Young Foundations and Trends® in Signal Processing 1 (3), 195-304, 2008 | 1224 | 2008 |
| Semi-tied covariance matrices for hidden Markov models MJF Gales IEEE transactions on speech and audio processing 7 (3), 272-281, 1999 | 759 | 1999 |
| Predictive uncertainty estimation via prior networks A Malinin, M Gales Advances in neural information processing systems 31, 2018 | 728 | 2018 |
| Robust continuous speech recognition using parallel model combination MJF Gales, SJ Young IEEE Transactions on Speech and Audio Processing 4 (5), 352-359, 1996 | 693 | 1996 |
| Mean and variance adaptation within the MLLR framework MJF Gales, PC Woodland Computer speech and language 10 (4), 249-264, 1996 | 627 | 1996 |
| Model-based techniques for noise robust speech recognition MJF Gales University of Cambridge, 1995 | 449 | 1995 |
| Cluster adaptive training of hidden Markov models MJF Gales IEEE transactions on speech and audio processing 8 (4), 417-428, 2000 | 380 | 2000 |
| An improved approach to the hidden Markov model decomposition of speech and noise MJF Gales, S Young [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics …, 1992 | 301 | 1992 |
| Cepstral parameter compensation for HMM recognition in noise MJF Gales, SJ Young Speech communication 12 (3), 231-239, 1993 | 273 | 1993 |
| Speech recognition using SVMs N Smith, M Gales Advances in neural information processing systems 14, 2001 | 230 | 2001 |
| The generation and use of regression class trees for MLLR adaptation MJF Gales University of Cambridge, Department of Engineering, 1996 | 210 | 1996 |
| Robust speech recognition in additive and convolutional noise using parallel model combination MFJ Gales, SJ Young Computer Speech & Language 9 (4), 289-307, 1995 | 208 | 1995 |
| The MGB challenge: Evaluating multi-genre broadcast media recognition P Bell, MJF Gales, T Hain, J Kilgour, P Lanchantin, X Liu, A McParland, ... 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015 | 182 | 2015 |
| Speech recognition and keyword spotting for low-resource languages: Babel project research at cued MJF Gales, KM Knill, A Ragni, SP Rath Fourth International workshop on spoken language technologies for under …, 2014 | 181 | 2014 |
| Ensemble distribution distillation A Malinin, B Mlodozeniec, M Gales arXiv preprint arXiv:1905.00076, 2019 | 180 | 2019 |
| HMM recognition in noise using parallel model combination. MJF Gales, SJ Young Eurospeech 93, 837-840, 1993 | 166 | 1993 |
| Data augmentation for low resource languages A Ragni, KM Knill, SP Rath, MJF Gales INTERSPEECH 2014: 15th Annual Conference of the International Speech …, 2014 | 151 | 2014 |
| Consensus network decoding for statistical machine translation system combination KC Sim, WJ Byrne, MJF Gales, H Sahbi, PC Woodland 2007 IEEE International Conference on Acoustics, Speech and Signal …, 2007 | 131 | 2007 |
Philip WoodlandProfessor of Information Engineering, Cambridge University Engineering DepartmentVerified email at eng.cam.ac.uk
