Joint acoustic modeling of triphones and trigraphemes by multi-task learning deep neural networks for low-resource speech recognition

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

Volumn , Issue , 2014, Pages 5592-5596

  Chen, Dongpeng ^a   Mak, Brian ^a   Leung, Cheung Chi ^b   Sivadas, Sunil ^b  

^a HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

^b INSTITUTE FOR INFOCOMM RESEARCH   (Singapore)

Author keywords

deep neural networks; multitask learning; trigrapheme modeling; triphone modeling

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING ALGORITHMS; SIGNAL PROCESSING; SPEECH RECOGNITION;

AFRICAN LANGUAGES; DEEP NEURAL NETWORKS; EXPERIMENTAL EVALUATION; GENERALIZATION PERFORMANCE; INTERNAL REPRESENTATION; LOW-RESOURCE SPEECH RECOGNITION; MULTITASK LEARNING; TRIPHONES;

LINEARIZATION;

EID: 84905283791     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2014.6854673     Document Type: Conference Paper

References (26)

1. K. U. Ogbureke and J. Carson-Berndsen, "Framework for cross-language automatic phonetic segmentation," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2010, pp. 5266-5269.
2. V. Le and L. Besacier, "Automatic speech recognition for under-resourced languages: Application to Vietnamese language," IEEE Transactions on Audio, Speech and Language Processing, vol. 17, no. 8, pp. 1471-1482, 2009.
3. J. Kohler, "Multi-lingual phoneme recognition exploiting acoustic-phonetic similarities of sounds," in Proceedings of the International Conference on Spoken Language Processing, 1996, pp. 1029-1032.
4. R. Caruana, Multitask Learning, Ph.D. thesis, Carnegie Mellon University, USA, 1997.
5. A. Mohamed, G.E. Dahl, and G. E. Hinton, "Acoustic modeling using deep belief networks," IEEE Transactions on Audio, Speech and Language Processing, vol. 20, no. 1, pp. 14-22, 2012.
6. S. Kanthak and H. Ney, "Context-dependent acoustic modeling using graphemes for large vocabulary speech recognition," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. IEEE, 2002, vol. 1, pp. 845-848.
7. P. Charoenpornsawat, S. Hewavitharana, and T. Schultz, "Thai grapheme-based speech recognition," in Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers. Association for Computational Linguistics, 2006, pp. 17-20.
8. S. Stuker, Acoustic Modeling for Under-Resourced Languages, Ph.D. thesis, University of Karlsruhe, Germany, 2009.
9. G. E. Hinton, S. Osindero, and Y. Teh, "A fast learning algorithm for deep belief nets," Neural computation, vol. 18, no. 7, pp. 1527-1554, 2006.
10. H. Lee, R. Grosse, R. Ranganath, and A. Y. Ng, "Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations," in Proceedings of the International Conference on Machine Learning. ACM, 2009, pp. 609-616.
11. R. Collobert and J. Weston, "A unified architecture for natural language processing: Deep neural networks with multitask learning," in Proceedings of the International Conference on Machine Learning. ACM, 2008, pp. 160-167.
12. S. Thrun and L. Pratt, Learning to Learn, Kluwer Academic Publishers, November 1997.
13. J.Baxter, "A model of inductive bias learning," Journal of Artificial Intelligence Research, vol. 12, pp. 149-198, 2000.
14. S. Ben-David and R. Schuller, "Exploiting task relatedness for multiple task learning," in Proceedings of COLT, 2003, pp. 567-580.
15. S. Parveen and P. D. Green, "Multitask learning in connectionist ASR using recurrent neural networks," in Proceedings of the European Conference on Speech Communication and Technology, 2003, pp. 1813-1816.
16. G. Tur, "Multitask learning for spoken language understanding," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2006, pp. 585-588.
17. Y. Huang,W.Wang, L.Wang, and T. Tan, "Multi-task deep neural network for multi-label learning," in Proceedings of the IEEE International Conference on Image Processing, 2013, pp. 2897-2900.
18. M. Seltzer and J. Droppo, "Multi-task learning in deep neural networks for improved phoneme recognition," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013, pp. 6965-6968.
19. Jui-Ting Huang, Jinyu Li, Dong Yu, Li Deng, and Yifan Gong, "Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013, pp. 7304-7308.
20. A. Ghoshal, P. Swietojanski, and S. Renals, "Multilingual training of deep-neural netowrks," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2013, pp. 7319-7323.
21. H. Hermansky, D. P. W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional hmm systems," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing. IEEE, 2000, vol. 3, pp. 1635-1638.
22. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on. IEEE, 1997, pp. 347-354.
23. A. Stolcke et al., "SRILM-an extensible language modeling toolkit.," in INTERSPEECH, 2002, pp. 901-904.
24. Meraka-Institute, "Lwazi ASR corpus," http://www. meraka.org.za/lwazi", 2009.
25. M.Davel M. Tempest, "Dictionarymaker 2.16 user manual," http://dictionarymaker.sourceforge. net/, 2009.
26. T. Ko and B. Mak, "Eigentrigraphemes for under-resourced languages," Speech Communication, vol. 56, pp. 132-141, 2014.