Multi-accent deep neural network acoustic model with accent-specific top layer using the KLD-regularized model adaptation

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

Volumn , Issue , 2014, Pages 2977-2981

  Huang, Yan ^a   Yu, Dong ^a   Liu, Chaojun ^a   Gong, Yifan ^a  

^a MICROSOFT   (United States)

Author keywords

Accent speech recognition; KL divergence regularization; Model adaptation

Indexed keywords

COMPUTATIONAL EFFICIENCY; INFORMATION RETRIEVAL SYSTEMS; SPEECH COMMUNICATION;

BASELINE MODELS; DEEP NEURAL NETWORKS; KL-DIVERGENCE; KNOWLEDGE-SHARING; MODEL ADAPTATION; PERFORMANCE GAIN; SPEECH SERVICES; WORD ERROR RATE REDUCTIONS;

SPEECH RECOGNITION;

EID: 84910100361     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (16)

1. Yu, D., Yao, K., Su, H., Li, G., and Seide, F., "KL-Divergence Regularized Deep Neural Network Adaptation for Improved Large Vocabulary Speech Recognition", in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
2. Huang, C., Chen, T., and Chang, E., "Accent Issues in Large Vocabulary Speech Recognition", in the International Journal of Speech Technology, vol. 7, no. 2, pp. 141-153, 2004.
3. Wang, Z., Schultz, T., and Waibel, A., "Comparison of Acoustic Model Adaptation Techniques on Non-native Speech", in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
4. Dahl, G.E., Yu, D., Deng, L., and Acero, A., "Context-Dependent Pre-trained Deep Neural Networks for Large Vocabulary Speech Recognition", IEEE Transactions on Audio, Speech, and Language Processing (TASLP) - Special Issue on Deep Learning for Spech and Language Processing, Volume: 1, No. 1, Page(s): 33- 42, Jan 2012.
5. Seide, F., Li, G., and Yu, D., "Conversational Speech Transcription Using Context-Dependent Deep Neural Networks", in the Proceedings of Interspeech 2012.
6. Kingsbury, B., Sainath, N. T., and Soltau, H., "Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization", in the Proceedings of Interspeech 2012.
7. Yu, D., Seltzer, M., Li, J., Huang, J., Seide, F., "Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks", in the Proceedings of 2013 International Confernece on Learning Representation, 2013.
8. Goodfellow, I. J., Le, Q. V., Saxe, A. M., Lee, H., and Ng, A. Y., "Measuring Invariances in Deep Networks", Advances in Neural Information Processing Systems (NIPS) 22, 2009.
9. Vergyri, D., Lamel, L., and Gauvain, L., "Automatic Speech Recognition of Multiple Accented English Data", in the Proceedings of the 2010 Interspeech conference, 2010.
10. Yanli Zheng, Y., Sproat, R., Gu, L., Shafran, I., Zhou, H., Su, Y., Jurafsky, D., Starr, R., and Yoon, S., "Accent Detection and Speech Recognition for Shanghai-accented Mandarin", in the Proceedings of the 2005 Interspeech conference, 2005.
11. Nallasamy, U., Metze, F., and Schultz, T., "Enhanced Polyphone Decision Tree Adaptation for accented-speech Recognition, in the Proceedings of the 2012 Interspeech conference, 2012.
12. Arslan, L. M. and Hansen, J. L., A Study of the Temporal Features and Frequency Characteristics in American English Foreign Accent, Journal of the Acoustic Society, America, December, 1996.
13. Huang, J., Li, J., Yu, D., Deng, L., and Gong, Y., "Cross-Language Knowledge Transfer Using Multilingual Deep Neural Network With Shared Hidden Layers", in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
14. Povey, D, Kingsbury, B., Ramabhadran, B., Saon, G., Soltau, H., and Visweswariah, K., "Boosted MMI for model and featurespace discriminative training", in the Proceedings of the 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008.
15. Povey, D, Kingsbury, B., Mangu, L., Saon, G., Soltau, H., and Zweig, G., "fMPE: Discriminatively Trained Features for Speech Recognition", in the Proceedings of the 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2005.
16. Su, H., Li, G., Yu, D., and Seide, F., "Error Back Propagation For Sequence Training Of Context-Dependent Deep Networks For Conversational Speech Transcription", in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.