Investigating online low-footprint speaker adaptation using generalized linear regression and click-through data

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 2015-August, Issue , 2015, Pages 4310-4314

  Zhao, Yong ^a   Li, Jinyu ^a   Xue, Jian ^a   Gong, Yifan ^a  

^a MICROSOFT   (United States)

Author keywords

automatic speech recognition; deep neural network; low footprint; speaker adaptation

Indexed keywords

AUDIO SIGNAL PROCESSING; CHEMICAL ACTIVATION; DIGITAL STORAGE; LINEAR TRANSFORMATIONS; MATHEMATICAL TRANSFORMATIONS; SINGULAR VALUE DECOMPOSITION; SPEECH COMMUNICATION; SPEECH RECOGNITION;

ACCURACY IMPROVEMENT; ACTIVATION FUNCTIONS; ADAPTATION ALGORITHMS; ADAPTATION TECHNIQUES; AUTOMATIC SPEECH RECOGNITION; LOW FOOTPRINT; SIGMOID ACTIVATION FUNCTION; SPEAKER ADAPTATION;

DEEP NEURAL NETWORKS;

EID: 84946061232     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2015.7178784     Document Type: Conference Paper

References (27)

1. G. E. Dahl, D. Yu, L. Deng, and A. Acero, Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition, IEEE Trans. Audio, Speech, Lang. Process., vol. 20, no. 1, pp. 30-42, 2012
2. N. Jaitly, P. Nguyen, A. Senior, and V. Vanhoucke, Application of pretrained deep neural networks to large vocabulary speech recognition, in Proc. Interspeech, 2012, pp. 2578-2581
3. L. Deng, J. Li, J.-T. Huang, et al., Recent advances in deep learning for speech research at Microsoft, in Proc. ICASSP, 2013, pp. 8604-8608
4. T. N. Sainath, B. Kingsbury, B. Ramabhadran, P. Fousek, P. Novak, and A. Mohamed, Making deep belief networks effective for large vocabulary continuous speech recognition, in Proc. ASRU, 2011, pp. 30-35
5. V. Abrash, H. Franco, A. Sankar, and M. Cohen, Connectionist speaker normalization and adaptation, in Proc. Eurospeech, 1995, pp. 2183-2186
6. J. Neto, L. Almeida, M. Hochberg, C. Martins, Lu. Nunes, S. Renals, and T. Robinson, Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system, in Proc. Eurospeech, 1995, pp. 2171-2174
7. B. Li and K. C. Sim, Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems, in Proc. Interspeech, 2010, pp. 526-529
8. X. Liu, M. J. F. Gales, and P. C. Woodland, Improving LVCSR system combination using neural network language model cross adaptation, in Proc. Interspeech, 2011, pp. 2857-2860
9. F. Seide, G. Li, X. Chen, and D. Yu, Feature engineering in context-dependent deep neural networks for conversational speech transcription, in Proc. ASRU, 2011, pp. 24-29
10. M. J. F. Gales, Maximum likelihood linear transformations for HMM-based speech recognition, Comput. Speech Lang., vol. 12, no. 2, pp. 75-98, Jan. 1998
11. R. Gemello, F. Mana, S. Scanzio, P. Laface, and R. De Mori, Linear hidden transformations for adaptation of hybrid ANN/HMM models, Speech Commun., vol. 49, no. 10, pp. 827-835, 2007
12. 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 Proc. SLT, 2012, pp. 366-369
13. J. Li, J.-T. Huang, and Y. Gong, Factorized adaptation for deep neural network, in Proc. ICASSP, 2014, pp. 5574-5578
14. J. Xue, J. Li, D. Yu, M. Seltzer, and Y. Gong, Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network, in Proc. ICASSP, 2014, pp. 6409-6413
15. S. M. Siniscalchi, J. Li, and C.-H. Lee, Hermitian based hidden activation functions for adaptation of hybrid HMM/ANN models, in Proc. INTERSPEECH, 2012, pp. 2590-2593
16. S. M. Siniscalchi, J. Li, and C.-H. Lee, Hermitian polynomial for speaker adaptation of connectionist speech recognition systems, IEEE Trans. Audio, Speech, Lang. Process., vol. 21, no. 10, pp. 2152-2161, 2013
17. P. Swietojanski and S. Renals, Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models, in Proc. SLT, 2014, pp. 171-176
18. J. Xue, J. Li, and Y. Gong, Restructuring of deep neural network acoustic models with singular value decomposition, in Proc. Interspeech, 2013, pp. 2365-2369
19. C. J. Leggetter and P. C. Woodland, Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models, Comput. Speech Lang., vol. 9, pp. 171-186, 1995
20. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, Learning representations by back-propagating errors, in Cognitive modeling. MIT Press, Cambridge, MA, 1988
21. D. Yu, K. Yao, H. Su, G. Li, and F. Seide, KL-divergence regularized deep neural network adaptation for improved large vocabulary speech recognition, in Proc. ICASSP, 2013, pp. 7893-7897
22. H. Y. Chan and P. C. Woodland, Improving broadcast news transcription by lightly supervised discriminative training, in Proc. ICASSP, 2004, pp. 737-740
23. D. Yu, B. Varadarajan, L. Deng, and A. Acero, Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion, Comput. Speech Lang., vol. 24, no. 3, pp. 433-444, 2010
24. K. Vesely, M. Hannemann, and L. Burget, Semi-supervised training of deep neural networks, in Proc. ASRU, 2013, pp. 267-272
25. Y. Huang, D. Yu, Y. Gong, and C. Liu, Semi-supervised GMM and DNN acoustic model training with multi-system combination and confidence re-calibration, in Proc. Interspeech, 2013, pp. 2360-2364
26. O. Siohan, Training data selection based on contextdependent state matching, in Proc. ICASSP, 2014, pp. 3316-3319
27. A. Senior and I. Lopez-Moreno, Improving DNN speaker independence with i-vector inputs, in Proc. ICASSP, 2014, pp. 225-229