Multi-view and multi-objective semi-supervised learning for HMM-based automatic speech recognition

IEEE Transactions on Audio, Speech and Language Processing

Volumn 20, Issue 7, 2012, Pages 1923-1935

  Cui, Xiaodong ^a   Huang, Jing ^a   Chien, Jen Tzung ^b  

^a IBM T J WATSON RESEARCH CENTER   (United States)

^b NATIONAL CHENG KUNG UNIVERSITY   (Taiwan)

Author keywords

Acoustic modeling; automatic speech recognition; multi objective learning; multi view committee machine; semi supervised learning (SSL)

Indexed keywords

ACOUSTIC MODELING; AUTOMATIC SPEECH RECOGNITION; COMMITTEE MACHINES; MULTI OBJECTIVE; SEMI-SUPERVISED LEARNING;

CONTINUOUS SPEECH RECOGNITION; DECISION TREES; ENTROPY; INFORMATION THEORY; TRANSCRIPTION;

SUPERVISED LEARNING;

EID: 84860878023     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2191955     Document Type: Conference Paper

References (45)

1. O. Chapelle, B. Scholokpf, and A. Zien, Semi-Supervised Learn.. Cambridge, MA: MIT Press, 2006.
2. X. Zhu, "Semi-supervised learning literature survey," Univ. of Wisconsin-Madison, Madison, Tech. Rep., 2006.
3. N. Nigam, A. K. McCallum, S. Thrun, and T. Mitchell, "Text classification from labeled and unlabeled documents using EM," Mach. Learn., vol. 39, pp. 103-134, 2000. (Pubitemid 30594822)
4. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc. Ser. B, vol. 39, no. 1, pp. 1-38, 1977.
5. M. Inoue and N. Ueda, "Exploitation of unlabeled sequences in hidden Markov models," IEEE Trans. Pattern Anal. Mach. Intell., vol. 25, no. 12, pp. 1570-1581, Dec. 2003.
6. S. Ji, L. T. Watson, and L. Carin, "Semi-supervised learning of hidden Markov models via a homotopy method," IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 2, pp. 275-287, Feb. 2009.
7. A. McCallum, C. Pal, G. Druck, and X. Wang, "Multiconditional learning: Generative/discriminative training for clustering and classification," in Proc. AAAI Nat. Conf. Artif. Intell., 2006, pp. 433-439. (Pubitemid 44705322)
8. J.-T. Huang and M. Hasegawa-Johnson, "On semi-supervised learning of Gaussian mixture models for phonetic classification," in NAACL HLT Workshop Semi-Supervised Learn. Natural Lang. Process., 2009, pp. 75-83.
9. A. Blum and T. Mitchell, "Combining labeled and unlabeled data with co-training," in Proc. Annu. Conf. Comput. Learn. Theory, 1998, pp. 92-100.
10. Z.-H. Zhou and M. Li, "Tri-training: Exploiting unlabeled data using three classifiers," IEEE Trans. Knowl. Data Eng., vol. 37, no. 11, pp. 1529-1541, Nov. 2005. (Pubitemid 41704840)
11. R. K. Ando and T. Zhang, "A framework for learning predictive structures from multiple tasks and unlabeled data," J. Mach. Learn. Res., vol. 36, pp. 1817-1853, 2005.
12. S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Trans. Knowl. Data Eng., vol. 22, no. 10, pp. 1345-1359, 2010.
13. J.-T. Chien and S. Furui, "Predictive hidden Markov model selection for speech recognition," IEEE Trans. Speech Audio Process., vol. 13, no. 3, pp. 377-387, May 2005. (Pubitemid 40666172)
14. U. Brefeld, T. Gartner, T. Scheffer, and S. Wrobel, "Efficient coregularised least squares regression," in Proc. Int. Conf. Mach. Learn., 2006, pp. 137-144.
15. Y. Grandvalet and Y. Bengio, "Semi-supervised learning by entropy minimization," in Advances in Neural Information Processing Systems 17. Cambridge, MA: MIT Press, 2005, pp. 529-536.
16. Y. Jin, Multi-Objective Machine Learning. Berlin, Heidelberg, Germany: Springer-Verlag , 2006.
17. J.-T. Chien and J.-C. Junqua, "Unsupervised hierarchical adaptatoin using reliable selection of cluster-dependent parameters," Speech Commun., vol. 30, no. 4, pp. 235-253, 2000. (Pubitemid 30557792)
18. F. Wessel and H. Ney, "Unsupervised training of acoustic models for large vocabulary continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 13, no. 1, pp. 23-31, Jan. 2005. (Pubitemid 40049937)
19. L. Wang, M. Gales, and P. C. Woodland, "Unsupervised training for Mandarin broadcast news and conversation transcription," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2007, pp. 353-356.
20. L. Lamel, J.-L. Gauvain, and G. Adda, "Lightly supervised and unsupervised acoustic model training," Comput. Speech Lang., vol. 16, pp. 115-129, 2002.
21. H. Soltau, G. Saon, B. Kingsbury, H.-K. J. Kuo, L. Mangu, D. Povey, and A. Emami, "Advances in Arabic speech transcription at IBM under the DARPA GALE program," IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 5, pp. 884-894, Jul. 2009.
22. S. Matsoukas, J.-L. Gauvain, G. Adda, T. Colthurst, C.-L. Kao, O. Kimball, L. Lamel, F. Lefevre, J. Z. Ma, J. Makhoul, L. Nguyen, R. Prasad, R. Schwartz, H. Schwenk, and B. Xiang, "Advances in transcription of broadcast news and conversational telephone speech within the combined EARS BBN/LIMSI system," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1541-1556, Sep. 2006.
23. M. Bacchiani and B. Roark, "Unsupervised language model adaptation," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2003, pp. 224-227.
24. B. Roark and M. Bacchiani, "Supervised and unsupervised PCFG adaptation to novel domains," in Proc. Conf. North Amer. Chapt. Assoc. Comput. Linguist. Human Lang. Technol., 2003, pp. 126-133.
25. G. Tur, "Co-adaptation: Adaptive co-training for semisupervised learning," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2009, pp. 3721-3724.
26. U. Guz, S. Cuendet, D. Hakkani-Tur, and G. Tur, "Multi-view semi-supervised learning for dialog act segmentation of speech," IEEE Trans. Audio, Speech, Lang. Process., vol. 18, no. 2, pp. 320-329, Feb. 2010.
27. G. Tur, D. Hakkani-Tur, and R. E. Schapire, "Combining active and semi-supervised learning for spoken language understanding," Speech Commun., no. 45, pp. 171-186, 2005. (Pubitemid 40220192)
28. D. Yu, B. Varadarajan, L. Deng, and A. Acero, "Active learning and semi-supervised learning for speech recognition: A unified framework using the global entropy reduction maximization criterion," Comput. Speech Lang., no. 24, pp. 433-444, 2010.
29. J. Huang, X. Cui, and J.-T. Chien, "Cross-view transfer learning for automatic speech recognition," in Proc. NIPS 2010 Workshop Transfer Learn. by Learn. Rich Generative Models, 2010.
30. K. M. Miettinen, Nonlinear Multiobjective Optimization. Norwell, MA: Kluwer Academic, 1998.
31. S. Yaman and C.-H. Lee, "A flexible classifier design framework based on multiobjective programming," IEEE Trans. Audio, Speech, Lang. Process., vol. 16, no. 4, pp. 779-789, May 2008.
32. X. Cui, J. Huang, and J.-T. Chien, "Multi-view and multiobjective semi-supervised learning for large vocabulary continuous speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2011, pp. 4668-4671.
33. X. Cui, J. Xue, B. Xiang, and B. Zhou, "A study of bootstrapping with multiple acoustic features for improved automatic speech recognition," in Proc. Annu. Conf. Int. Speech Commun. Assoc., 2009, pp. 240-243.
34. O. Siohan, B. Ramabhadran, and B. Kingsbury, "Constructing ensembles of ASR systems using randomized decision trees," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2005, pp. 197-200.
35. J. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER)," in Proc. IEEE Workshop Autom. Speech Recognit. Understand., 1997, pp. 347-354.
36. F. Grezl, M. Karafiat, S. Kontar, and J. Cernocky, "Probabilistic and bottle-neck features for LVCSR of meetings," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2007, pp. 757-760.
37. B. Kingsbury, "Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2009, pp. 3761-3764.
38. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5-32, 2001. (Pubitemid 32933532)
39. L. R. Bahl, P. F. Brown, P. V. de Souza, and R. L. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition," in Proc. Int. Conf. Acoust., Speech, Signal Process., 1986, pp. 49-52.
40. A. Berger, S. D. Pietra, and V. D. Pietra, "A maximum entropy approach to natural language processing," Comput. Linguist., vol. 22, no. 1, pp. 39-71, 1996.
41. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for model and feature-space discriminative training," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2008, pp. 4057-4060.
42. G. Saon and D. Povey, "Penalty function maximization for large margin HMM training," in Proc. Annu. Conf. Int. Speech Commun. Assoc., 2008, pp. 920-923.
43. C. Ma, J. Kuo, H. Soltau, X. Cui, U. Chaudhari, L. Mangu, and C.-H. Lee, "A comparative study on system combination schemes for LVCSR," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2010, pp. 4394-4397.
44. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Univ. of Cambridge, Cambridge, U.K., 2003.
45. F. Sha and L. K. Saul, "Large margin hidden Markov models for automatic speech recognition," in Advances in Neural Information Processing Systems 19. Cambridge, MA: MIT Press, 2007, pp. 1249-1256.