Adaptation of context-dependent deep neural networks for automatic speech recognition

2012 IEEE Workshop on Spoken Language Technology, SLT 2012 - Proceedings

Volumn , Issue , 2012, Pages 366-369

  Yao, Kaisheng ^a   Yu, Dong ^b   Seide, Frank ^c   Su, Hang ^c,d   Deng, Li ^b   Gong, Yifan ^a  

^a MICROSOFT   (United States)

^b MICROSOFT RESEARCH   (United States)

^c MICROSOFT RESEARCH ASIA   (China)

^d TSINGHUA UNIVERSITY   (China)

Author keywords

Context Dependent Deep Neural Networks; HMM; speaker adaptation; speech recognition

Indexed keywords

ADAPTATION METHODS; AFFINE TRANSFORMATIONS; AUTOMATIC SPEECH RECOGNITION; BATCH UPDATE; CONTEXT DEPENDENT; DEEP NEURAL NETWORKS; HIDDEN LAYERS; HMM; INPUT LAYERS; LARGE VOCABULARY SPEECH RECOGNITION; LAYER ADAPTATION; SPEAKER ADAPTATION; STOCHASTIC GRADIENT ASCENTS; WORD ERROR RATE;

HIDDEN MARKOV MODELS; NEURAL NETWORKS; OPTICS;

SPEECH RECOGNITION;

EID: 84874226579     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SLT.2012.6424251     Document Type: Conference Paper

References (17)

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. on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 30-42, 2012.
2. G. Hinton, L. Deng, D. Yu, G. Dahl, A.-R. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition," IEEE Signal Processing Magazine, 2012.
3. X. Huang, A. Acero, and H.-W. Hong, Spoken Language Processing: a guide to theory, algorithm, and system development, Prentice Hall, 2001.
4. B. Li and K. C. Sim, "Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems," in INTERSPEECH, 2010, pp. 526-529.
5. R. Gemello, F. Mana, S. Scanzio, P. Laface, and R. D. Mori, "Adaptation of hybrid ANN/HMM models using linear hidden transformations and conservative training," in ICASSP, 2006, pp. 1189-1192.
6. S. M. Siniscalchi, J. Li, and C.-H. Lee, "Hermitian based hidden activation functions for adaptation of hybrid HMM/ANN models," in INTERSPEECH, 2012.
7. J. Neto et al, "Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system," in EUROSPEECH, 1995.
8. Arthur Earl Bryson and Yu-Chi Ho, Applied optimal control: optimization, estimation, and control, p. 481, Blaisdell Publishing Company or Xerox College Publishing, 1969.
9. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in ASRU, 2011.
10. P. Zhan etal, "Vocal tract length normalization for LVCSR," in Tech. Rep. CMU-LTI-97-150. Carnegie Mellon University, 1997.
11. M. J. F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer, Speech and Language, vol. 12, pp. 75-98, 1998.
12. V. Abrash, H. Franco, A. Sankar, and M. Cohen, "Connectionist speaker normalization and adaptation," in EUROSPEECH, 1995.
13. A. Mohamed, G. Dahl, and G. Hinton, "Acoustic modeling using deep belief networks," IEEE Trans. on Audio, Speech, and Language Processing, vol. 20, no. 1, pp. 14-22, 2012.
14. G. E. Hinton, "Training products of experts by minimizing contrastive divergence," Neural Computation, vol. 14, pp. 1771-1800, 2002.
15. G. Heigold, H. Ney, P. Lehnen, T. Gass, and R. Schluter, "Equivalence of generative and log-linear models," IEEE Trans. on Audio, Speech, and Language Processing, vol. 19, no. 5, pp. 1138-1148, 2011.
16. X. Li and J. Bilmes, "Regularized adaptation of discriminative classifiers," in ICASSP, 2006.
17. N. Kumar and A. G. Andreou, "A generalization of linear dis-criminant analysis in maximum likelihood framework," in Tech. Rep. JHU-CLSP Technical Report. Johns Hopkins University, Aug 1996, vol. 16.