Towards better performance with heterogeneous training data in acoustic modeling using deep neural networks

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

Volumn , Issue , 2014, Pages 845-849

  Huang, Yan ^a   Slaney, Malcolm ^a   Seltzer, Michael L ^a   Gong, Yifan ^a  

^a MICROSOFT   (United States)

Author keywords

CD DNN HMM; Channel compensation; Deep learning; Multi task learning; Noise robustness

Indexed keywords

SPEECH COMMUNICATION;

CD-DNN-HMM; CHANNEL COMPENSATION; DEEP LEARNING; MULTITASK LEARNING; NOISE ROBUSTNESS;

SPEECH RECOGNITION;

EID: 84910069710     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (24)

1. 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 Speech and Language Processing, Volume: 1, No. 1, Page(s): 33-42, Jan 2012.
2. Seide, F., Li, G., and Yu, D., "Conversational Speech Transcription Using Context-Dependent Deep Neural Networks, " in the Proceedings of Interspeech 2012.
3. 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.
4. Jaitly, N., Nguyen, P., Senior, A., and Vanhoucke, V., "Application of Pretrained Deep Neural Networks to Large Vocabulary Speech Recognition, " in the Proceedings of Interspeech 2012.
5. Deng, L., Li, J., Huang, J., Yao, K., Yu, D., Seide, F., Seltzer, M., Zweig, G., He, X., Williams, J., Gong, Y., and Acero, A., "Recent Advances in Deep Learning for Speech Research at Microsoft, " in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
6. Huang, Y., Yu, D., Liu, C., and Gong, Y., "A Comparative Analytic Study on the Gaussian Mixture and Context Dependent Deep Neural Network Hidden Markov Models, " submitted to the Interspeech 2014.
7. Gales, M. J. F., "Cluster adaptive training of hidden Markov models, " IEEE Trans. Speech Audio Processing, vol. 8, no. 4, pp. 417-428, July 2000.
8. Yu, K., "Adaptive Training for Large Vocabulary Continuous Speech Recognition, " Ph.D. Thesis, Cambridge University, 2006.
9. Gales, M. J. F., "Acoustic Factorisation, " in Proceedings of ASRU 2001.
10. Wang, Y., Gales, M. J. F., "Speaker and Noise Factorization for Robust Speech Recognition, " in IEEE Transactions on Audio, Speech, and Language Processing (TASLP), VOL. 20, NO. 7, September 2012.
11. Seide, F., Li, G., Chen, X., and Yu, D., "Feature Engineering in Context-Dependent Deep Neural Networks for Conversational Speech Transcription, " in the Proceedings of the ASRU, 2011.
12. Li, B. and Sim, K. C., "Comparison of Discriminative Input and Output Transformations for SpeakerAdaptation in the Hybrid NN/HMM Systems, " in the Proceedings of Interspeech 2010.
13. Hank, L., " Speaker Adaptation of Context Dependent Deep Neural Networks, " in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
14. Gong, Y., "Stochastic trajectory modeling and sentence searching for continuous speech recognition, " IEEE Transactions on Speech Audio Processing, vol. 5, no. 1, pp. 3344, 1997.
15. Korkmazskiy, F., Juang, B. H., and Soong, F. K. Generalized mixture of HMMs for continuous speech recognition, in the Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 1997.
16. Zhao, Y. and Juang, B. H., "Modeling Heterogeneous Data Sources for Speech Recognition Using Synchronous Hidden Markov Models, " in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
17. Seltzer, M., Yu, D., Wang, Y., "An Investigation of Deep Neural Networks for Noise Robust Speech Recognition, " in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
18. Abdel-Hamid, O. and Jiang, H., "Fast Speaker Adaptation of Hybrid NN/HMM Model for Speech Recognition Based on Discriminative Learning of Speaker Code, " in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
19. Saon, G., Soltau, H., Nahamoo, D., and Picheny, M., "Speaker Adaptation of Neural Network Acoustic Models Using I-Vectors, " in the Proceedings of the ASRU 2013.
20. 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.
21. Arnab, G., Pawel, S. and Steve, R., "Multilingual training of deep neural networks, " in the Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2013.
22. Yu, D., Seltzer, M., Li, J., Huang, J., and Seide, F., "Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks, " in the Proceedings of 2013 International Confernece on Learning Representation, 2013.
23. 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.
24. 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.