Context-dependent modelling of deep neural network using logistic regression

2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

Volumn , Issue , 2013, Pages 338-343

  Wang, Guangsen ^a   Sim, Khe Chai ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Articulatory Features; Canonical State Modelling; Context Dependent Modelling; Deep Neural Network; Logistic Regression

Indexed keywords

ARTICULATORY FEATURES; AUTOMATIC SPEECH RECOGNITION; BROADCAST NEWS TRANSCRIPTIONS; CONTEXT DEPENDENT; DATA SPARSITY PROBLEMS; DEEP NEURAL NETWORKS; LOGISTIC REGRESSIONS; REGRESSION PARAMETERS;

DECISION TREES; NEURAL NETWORKS; REGRESSION ANALYSIS; TELEPHONE SETS;

SPEECH RECOGNITION;

EID: 84893699565     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2013.6707753     Document Type: Conference Paper

References (22)

1. S. J. Young, J. J. Odell, and P. C.Woodland, "Tree-based state tying for high accuracy acoustic modelling, " in HLT, 1994, pp. 307-312.
2. N. Morgan and H. Bourlard, "Neural networks for statistical recognition of continuous speech, " Proc. IEEE, vol. 83, pp. 742-772, 1995.
3. H. Franco, M. Cohen, N. Morgan, D. Rumelhart, and V. Abrash, "Context-dependent connectionist probability estimation in a hybrid hidden markov model-neural net speech recognition system, " Computer Speech and Language, vol. 8, pp. 211-222, July 1994.
4. G. Wang and K. C. Sim, "Comparison of smoothing techniques for robust context dependent acoustic modelling in hybrid NN/HMM systems, " in Interspeech, 2011, pp. 457-460.
5. G. Wang and K. C. Sim, "Sequential classification criteria for NNs in automatic speech recognition, " in Interspeech, 2011, pp. 441-444.
6. G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks." Science, vol. 313, no. 5786, pp. 504-507, 2006. (Pubitemid 44148451)
7. G. E. Hinton, S. Osindero, and Y.-W. Teh, "A fast learning algorithm for deep belief nets, " Neural Computation, vol. 18, pp. 1527-1554, 2006. (Pubitemid 44024729)
8. G. E. Dahl, D. Y. L. Deng, and A. Acero, "Context-dependent pretrained deep neural networks for large vocabulary speech recognition, " IEEE Trans. on ASLP, vol. 20, pp. 30-42, 2012.
9. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in contextdependent deep neural networks for conversational speech transcription, " in ASRU, 2011, pp. 24-29.
10. T. N. Sainath, B. Kingsbury, and etc, "Making deep belief networks effective for large vocabulary continuous speech recognition, " in ASRU, 2011, pp. 30-35.
11. G. Hinton, L. Deng, D. Yu, and etc, "Deep neural networks for acoustic modeling in speech recognition, " IEEE Signal Processing Magazine, vol. 29, pp. 82-97, 2012.
12. A. Mohamed, G. E. Dahl, and G. E. Hinton, "Acoustic modeling using deep belief networks, " IEEE Trans. ASLP, vol. 20, no. 1, pp. 14-22, 2012.
13. M. J. F. Gales and K. Yu, "Canonical state models for automatic speech recognition, " in Interspeech, 2010, pp. 58-61.
14. C.-H. Lee, M. Clements, S. Dusan, E. Fosler-Lussier, and etc, "An Overview on Automatic Speech Attribute Transcription (ASAT), " in Proc. InterSpeech, 2007.
15. S. M. Siniscalchi, D. Yu, L. Deng, and C.-H. Lee, "Exploiting deep neural networks for detection-based speech recognition, " Neurocomput., vol. 106, pp. 148-157, Apr. 2013.
16. L. Deng and D. Sun, "A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features, " J. Acou. Soc. Am., vol. 95, no. 5, pp. 2702-2719.
17. D. Povey and L. B. et al., "The subspace gaussian mixture modela structured model for speech recognition, " Comput. Speech Lang., vol. 25, pp. 404-439, 2011.
18. M. J. F. Gales, "The generation and use of regression class trees for MLLR adaptation, " Cambridge University Engineering Department, Tech. Rep., 1996.
19. K. Yu, H. Zen, F. Mairesse, and S. Young, "Context adaptive training with factorized decision trees for HMM-based statistical parametric speech synthesis, " Speech Commun., vol. 53, no. 6, pp. 914-923, 2011.
20. P. Schwarz, "Phoneme recognition based on long temporal context, " Ph.D. dissertation, Brno University of Technology, Faculty of Information Technology, 2008.
21. V. Valtchev, J. J. Odell, P. C.Woodland, and S. J. Young, "MMIE training of large vocabulary recognition systems, " Speech Comm., vol. 22, no. 4, pp. 303 - 314, 1997. (Pubitemid 127433601)
22. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, and etc, "The kaldi speech recognition toolkit, " in IEEE 2011 Workshop on Automatic Speech Recognition and Understanding, 2011.