Deep neural network features and semi-supervised training for low resource speech recognition

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

Volumn , Issue , 2013, Pages 6704-6708

  Thomas, Samuel ^a   Seltzer, Michael L ^b   Church, Kenneth ^c   Hermansky, Hynek ^a  

^a JOHNS HOPKINS UNIVERSITY   (United States)

^b MICROSOFT RESEARCH   (United States)

^c IBM RESEARCH   (United States)

Author keywords

bottleneck features; deep neural networks; Low resource; semi supervised training; speech recognition

Indexed keywords

ACOUSTIC MODEL; BOTTLENECK FEATURES; DEEP NEURAL NETWORKS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LOW RESOURCE; LOW-RESOURCE SETTINGS; LOW-RESOURCE SPEECH RECOGNITION; SEMI-SUPERVISED TRAININGS;

CONTINUOUS SPEECH RECOGNITION; SIGNAL PROCESSING; SPEECH RECOGNITION;

NEURAL NETWORKS;

EID: 84890474716     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6638959     Document Type: Conference Paper

References (38)

1. H. Lin, L. Deng, D. Yu, Y. Gong, A. Acero, and C.H. Lee, "A study on multilingual acoustic modeling for large vocabulary ASR," in IEEE ICASSP, 2009
2. D. Imseng, J. Dines, P. Motlicek, P.N. Garner, and H. Bourlard, "Comparing different acoustic modeling techniques for multilingual boosting," in ISCA Interspeech, 2012
3. L. Burget, P. Schwarz, M. Agarwal, P. Akyazi, K. Feng, A. Ghoshal, O. Glembek, N. Goel, M. Karafiat, D. Povey, et al., "Multilingual acoustic modeling for speech recognition based on subspace Gaussian mixture models," in IEEE ICASSP, 2010
4. L. Lu, A. Ghoshal, and S. Renals, "Regularized subspace Gaussian mixture models for cross-lingual speech recognition," in IEEE ASRU, 2011
5. Y. Qian, D. Povey, and J. Liu, "State-level data borrowing for low-resource speech recognition based on subspace GMMs," in ISCA Interspeech, 2011
6. S. Sivadas and H. Hermansky, "On use of task independent training data in tandem feature extraction," in IEEE ICASSP, 2004
7. A. Stolcke, F. Grezl, M.Y. Hwang, X. Lei, N. Morgan, and D. Vergyri, "Cross-domain and cross-language portability of acoustic features estimated by multilayer perceptrons," in IEEE ICASSP, 2006
8. S. Thomas, S. Ganapathy, and H. Hermansky, "Cross-lingual and multistream posterior features for low resource LVCSR systems," in ISCA Interspeech, 2010
9. Y. Qian and J. Liu, "Cross-lingual and ensemble MLPs-Strategies for low-resource speech recognition," in ISCA Interspeech, 2012
10. N. Thang, B. Wojtek, F. Metze, and T. Schultz, "Initialization schemes for multilayer perceptron training and their impact on ASR performance using multilingual data," in ISCA Interspeech, 2012
11. S. Thomas, S. Ganapathy, and H. Hermansky, "Multilingual MLP features for low-resource LVCSR systems," in IEEE ICASSP, 2012
12. S. Thomas, S. Ganapathy, A. Jansen, and H. Hermansky, "Data-driven posterior features for low resource speech recognition applications," in ISCA Interspeech, 2012
13. F. Seide, G. Li, X. Chen, and D. Yu, "Feature engineering in context-dependent deep neural networks for conversational speech transcription," in IEEE ASRU, 2011
14. G. Hinton, L. Deng, D. Yu, G. Dahl, A. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. Sainath, and B. Kingsbury, "Deep neural networks for acoustic modeling in speech recognition," in IEEE Signal Processing Magazine, 2012
15. D. Erhan, Y. Bengio, A. Courville, P.A. Manzagol, P. Vincent, and S. Bengio, "Why does unsupervised pre-training help deep learning?," JMLR, 2010
16. D. Yu, L. Deng, and G. Dahl, "Roles of pre-training and fine-tuning in context-dependent DBN-HMMs for real-world speech recognition," in NIPS Workshop, 2010
17. G.E. Dahl, D. Yu, L. Deng, and A. Acero, "Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition," IEEE TASLP, 2012
18. D. Yu and M.L. Seltzer, "Improved bottleneck features using pretrained deep neural networks," ISCA Interspeech, 2011
19. T.N. Sainath, B. Kingsbury, and B. Ramabhadran, "Autoencoder bottleneck features using deep belief networks," in IEEE ICASSP, 2012
20. T.N. Sainath, B. Kingsbury, B. Ramabhadran, P. Fousek, P. Novak, and A.R. Mohamed, "Making deep belief networks effective for large vocabulary continuous speech recognition," in IEEE ASRU, 2011
21. G.E. Hinton, S. Osindero, and Y.W. Teh, "A fast learning algorithm for deep belief nets," Neural computation, 2006
22. Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, "Greedy layer-wise training of deep networks," Advances in neural information processing systems, 2007
23. F. Grezl, M. Karafiat, S. Kontar, and J. Cernocky, "Probabilistic and bottle-neck features for lvcsr of meetings," in IEEE ICASSP, 2007
24. B. Chen, Q. Zhu, and N. Morgan, "Learning long-term temporal features in lvcsr using neural networks," in ISCA ICSLP, 2004
25. A. Canavan, D. Graff, and G. Zipperlen, "Callhome american english speech," LDC, 1997
26. A. Canavan, D. Graff, and G. Zipperlen, "Callhome german speech," LDC, 1997
27. A. Canavan and G. Zipperlen, "Callhome spanish speech," LDC, 1997
28. J. Godfrey, E. Holliman, and J. McDaniel, "Switchboard: Telephone speech corpus for research and development," in IEEE ICASSP, 1992
29. D. Graff, J. Kong, K. Chen, and K. Maeda, "English gigaword," LDC, 2003
30. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," The Journal of the Acoustical Society of America, 1990
31. S. Thomas, S. Ganapathy, and H. Hermansky, "Phoneme recognition using spectral envelope and modulation frequency features," in IEEE ICASSP, 2009
32. G. Zavaliagkos, M. Siu, T. Colthurst, and J. Billa, "Using untranscribed training data to improve performance," in ISCA ICSLP, 1998
33. T. Kemp and A. Waibel, "Unsupervised training of a speech recognizer: Recent experiments," in ISCA Eurospeech, 1999
34. L. Lamel, J.L. Gauvain, and G. Adda, "Unsupervised acoustic model training," in IEEE ICASSP, 2002
35. J. Ma, S. Matsoukas, O. Kimball, and R. Schwartz, "Unsupervised training on large amounts of broadcast news data," in IEEE ICASSP, 2006
36. S. Novotney and R. Schwartz, "Analysis of low-resource acoustic model self-training," in ISCA Interspeech, 2009
37. T. Kemp and T. Schaaf, "Estimating confidence using word lattices," in ISCA Eurospeech, 1997
38. L. Burget, P. Schwarz, P. Matejka, M. Hannemann, A. Rastrow, C. White, S. Khudanpur, H. Hermansky, and J. Cernocky, "Combination of strongly and weakly constrained recognizers for reliable detection of OOVs," in IEEE ICASSP, 2008.