Multi-task learning in deep neural networks for improved phoneme recognition

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

Volumn , Issue , 2013, Pages 6965-6969

  Seltzer, Michael L ^a   Droppo, Jasha ^a  

^a MICROSOFT RESEARCH   (United States)

Author keywords

Acoustic model; deep neural network; multi task learning; speech recognition; TIMIT

Indexed keywords

ACOUSTIC MODEL; CLASSIFICATION TASKS; DEEP NEURAL NETWORKS; FEED-FORWARD NETWORK; MULTITASK LEARNING; PHONEME RECOGNITION; SHARED REPRESENTATIONS; TIMIT;

NETWORK ARCHITECTURE; SIGNAL PROCESSING; SPEECH RECOGNITION; TELEPHONE SETS;

NEURAL NETWORKS;

EID: 84890545600     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6639012     Document Type: Conference Paper

References (14)

1. A. Mohamed, G.E. Dahl, and G. Hinton, "Acoustic modeling using deep belief networks," Audio, Speech, and Language Processing, IEEE Transactions on, vol. 20, no. 1, pp. 14-22, jan. 2012
2. F. Seide, G. Li, and D. Yu, "Conversational speech transcrip-tion using context-dependent deep neural networks," in Proc. Interspeech, 2011
3. B. Kingsbury, T. N. Sainath, and H. Soltau, "Scalable mini-mum bayes risk training of deep neural network acoustic mod-els using distributed hessian-free optimization," in Proc. Inter-speech, 2012
4. Rich Caruana, "Multitask learning: A knowledge-based source of inductive bias," Machine Learning, vol. 28, pp. 41-75, 1997
5. S. Parveen and P. D. Green, "Multitask learning in connection-ist ASR using recurrent neural networks," in Proc. Eurospeech, 2003
6. Y. Lu, F. Lu, S. Sehgal, S. Gupta, J. Du, C. H. Tham, P. Green, and V. Wan, "Multitask learning in connectionist speech recognition," in Proc. Australian International Conference on Speech Science and Technology, dec 2004
7. G. Tur, "Multitask learning for spoken language understand-ing, " in Proc. ICASSP, may 2006
8. X. Li, Y.-Y. Wang, and G. Tur, "Multi-task learning for spo-ken language understanding with shared slots," in Proc. Inter-speech, 2011
9. R. Collobert and J. Weston, "A unified architecture for natu-ral language processing: Deep neural networks with multitask learning," in International Conference on Machine Learning, ICML, 2008
10. L. Saul, T. Jaakkola, and M. I. Jordan, "Mean field theory for sigmoid belief networks," Journal of Artificial Intelligence Research, vol. 4, pp. 61-76, 1996
11. G. Hinton, "A practical guide to training restricted boltzmann machines," Tech. Rep. UTML TR 2010-003, University of Toronto, 2010
12. S. Renals, N. Morgan, H. Bourlard, M. Cohen, and H. Franco, "Connectionist probability estimators in hmm speech recogni-tion," Speech and Audio Processing, IEEE Transactions on, vol. 2, no. 1, pp. 161-174, Jan
13. J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, D. S. Pallett, and N. L. Dahlgren, "The DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus CDROM," 1986
14. K.-F. Lee and H.-W. Hon, "Speaker-independent phone recog-nition using hidden markov models," IEEE Transactions on Audio, Speech &Language Processing, vol. 37, no. 11, pp. 1641-1648, 1989.