FMLLR based feature-space speaker adaptation of DNN acoustic models

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn 2015-January, Issue , 2015, Pages 3630-3634

  Parthasarathi, Sree Hari Krishnan ^a   Hoffmeister, Bjorn ^a   Matsoukas, Spyros ^a   Mandal, Arindam ^a   Strom, Nikko ^a   Garimella, Sri ^a  

^a AMAZON   (United States)

Author keywords

DNN acoustic models; Feature space speaker adaptation; Speech recognition

Indexed keywords

MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD; MAXIMUM LIKELIHOOD ESTIMATION; SPEECH COMMUNICATION;

ACOUSTIC MODEL; EARLY FUSION; FEATURE SPACE; MAXIMUM LIKELIHOOD LINEAR REGRESSION; SIDE INFORMATION; SPEAKER ADAPTATION; TARGET MODEL; UNSUPERVISED ADAPTATION;

SPEECH RECOGNITION;

EID: 84959134917     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (21)

1. G. Hinton, L. Deng, D. Yu, G. Dahl, A. R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups, " IEEE Signal Processing Magazine, vol. 29, pp. 82-97, 2012.
2. H. Bourlard and N. Morgan, Connectionist speech recognition-a hybrid approach. Kluwer Academic Publishers, 1994.
3. H. Hermansky, D. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventionalHMMsystems, " in In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2000.
4. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context dependent deep neural networks for conversational speech transcription, " in In Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2011.
5. G. Saon, H. Soltau, D. Nahamoo, and M. Picheny, "Speaker adaptation of neural network acoustic models using i-vectors, " in In Proceedings of IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013.
6. T. Sainath, B. Kingsbury, H. Soltau, and B. Ramabhadran, "Optimization techniques to improve training speed of deep neural networks for large speech tasks, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, pp. 2267-2276, 2013.
7. R. Serizel and D. Giuliani, "Vocal tract length normalisation approaches to DNN-based children's and adults' speech recognition, " in In Proceedings of IEEE Spoken Language Technology (SLT) Workshop, 2014.
8. S. Xue, O. Abdel-Hamid, H. Jiang, L. Dai, and Q. Liu, "Fast adaptation of deep neural network based on discriminant codes for speech recognition, " ACM/IEEE Transactions on Audio, Speech, and Language Processing, vol. 22, pp. 1713-1725, 2014.
9. K. Yao, D. Yu, F. Seide, H. Su, L. Deng, and Y. Gong, "Adaptation of context-dependent deep neural networks for automatic speech recognition, " in In Proceedings of IEEE Spoken Language Technology (SLT) Workshop, 2012.
10. H. Liao, "Speaker adaptation of context dependent deep neural networks, " in In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013.
11. P. Swietojanski and S. Renals, "Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models, " in In Proceedings of IEEE Spoken Language Technology (SLT) Workshop, 2014.
12. S. Garimella, A. Mandal, N. Strom, B. Hoffmeister, S. Matsoukas, and S. H. K. Parthasarathi, "Robust i-vector based adaptation of DNN acoustic model for speech recognition, " in In Proceedings of Interspeech, 2015.
13. A. Senior and I. Lopez-Moreno, "Improving DNN speaker independence with i-vector inputs, " in In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2014.
14. Y. J, J. Clune, Y. Bengio, and H. Lipson, "How transferable are features in deep neural networks" in In Proceedings of Advances in Neural Information Processing Systems 27, 2014.
15. C. J. Leggetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models, " Computer Speech and Language, no. 9, 1995.
16. M. J. F. Gales and P. C. Woodland, "Mean and variance adaptation within the MLLR framework, " Computer Speech and Language, vol. 10, pp. 249-264, 1996.
17. L. Lee and R. Rose, "A frequency warping approach to speaker normalization, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 6, pp. 49-60, 1998.
18. S. Wegmann, D. McAllaster, J. Orloff, and B. Peskin, "Speaker normalization on conversational telephone speech, " in In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 1996.
19. S. H. K. Parthasarathi, S. Y. Chang, J. Cohen, N. Morgan, and S. Wegmann, "The blame game in meeting room ASR: An analysis of feature versus model errors in noisy and mismatched conditions, " in In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013.
20. G. Stemmer, F. Brugnara, and D. Giuliani, "Adaptive training using simple target models, " in In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
21. J. Kittler, M. Hatef, R. P. W. Duin, and J. Matas, "On combining classifiers. " IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, pp. 226-239, 1998.