Hidden markov acoustic modeling with bootstrap and restructuring for low-resourced languages

IEEE Transactions on Audio, Speech and Language Processing

Volumn 20, Issue 8, 2012, Pages 2252-2264

  Cui, Xiaodong ^a   Xue, Jian ^a   Chen, Xin ^b   Olsen, Peder A ^a   Dognin, Pierre L ^a   Chaudhari, Upendra V ^a   Hershey, John R ^c   Zhou, Bowen ^a  

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

^b PEARSON   (United States)

^c MITSUBISHI ELECTRIC RESEARCH LABORATORIES   (United States)

Author keywords

Bagging; bootstrap and restructuring; hidden Markov model (HMM); large vocabulary continuous speech recognition (LVCSR); low resourced language

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODELING; AUTOMATIC SPEECH RECOGNITION; BAGGING; BOOTSTRAP AND RESTRUCTURING; CLUSTERING CRITERIA; COVARIANCE MODELS; DATA SPARSITY; DECODING SPEED; GAUSSIANS; HIDDEN MARKOV MODELS (HMMS); LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; LAST STAGE; LOW-RESOURCED LANGUAGE; MEMORY CONSUMPTION; MODEL REFINEMENT; MODEL SIZE; PREDICTION CAPABILITY; REAL-WORLD APPLICATION; RUNTIMES; SEQUENCE PREDICTION; STATISTICAL RELIABILITY; TRAINING DATA; TRAINING PROCEDURES;

CONTINUOUS SPEECH RECOGNITION; HIDDEN MARKOV MODELS; VOCABULARY CONTROL;

AGGREGATES;

EID: 84865265602     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2199982     Document Type: Article

References (44)

1. S. T. Abate and W. Menzel, "Automatic speech recognition for an under-resourced language - Amharic," in Proc. Interspeech, 2007, pp. 1541-1544.
2. T. Pellegrini and L. Lamel, "Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language," in Proc. Interspeech, 2007, pp. 1797-1800.
3. V.-B. Le and L. Besacier, "Automatic speech recognition for under-resourced languages: Application to Vietnamese language," IEEE Trans. Audio, Speech, Lang. Process., vol. 17, no. 8, pp. 1471-1482, Nov. 2009.
4. T. Schultz and A. Waibel, "Language-independent and language-adaptive acoustic modeling for speech recognition," Speech Commun., vol. 35, pp. 31-51, 2001. (Pubitemid 32599645)
5. C. Nieuwoudt and E. C. Botha, "Cross-language use of acoustic information for automatic speech recognition," Speech Commun., vol. 38, pp. 101-113, 2002. (Pubitemid 34873601)
6. C.V. Heerden, N. Kleynhans, E. Barnard, and M. Davel, "Pooling ASR data for closely related languages," in Proc. Workshop Spoken Lang. Technol. for Under-Resourced Lang. (SLTU), 2010, pp. 17-23.
7. T. Schultz and K. Kirchhoff, Multilingual Speech Processing. New York: Elsevier, Academic, 2006.
8. B. Efron, "Bootstrap methods: Another look at the jackknife," Ann. Statist., vol. 1, no. 1, pp. 1-26, 1979.
9. B. Efron, "Nonparametric estimates of standard error: The jackknife, the bootstrap and other methods," Biometrika, vol. 68, no. 3, pp. 589-599, 1981.
10. B. Efron and R. Tibshirani, An Introduction to the Bootstrap. Boca Raton, FL: Chapman & Hall/CRC, 1993.
11. A. Davison, D. V. Hinkley, and A. Canty, Bootstrap Methods and Their Application. Cambridge, U.K.: Cambridge Univ. Press, 1999.
12. A. M. Zoubir and D. R. Iskander, Bootstrap Techniques for Signal Processing. Cambridge, U.K.: Cambridge Univ. Press, 2004.
13. L. Breiman, "Baggging predictors," Mach. Learn., vol. 24, no. 2, pp. 123-140, 1996.
14. L. Breiman, "Heuristics of instability and stabilization in model selection," Ann. Statist., vol. 24, no. 6, pp. 2350-2383, 1996.
15. X. Cui, J. Xue, P. L. Dognin, U. V. Chaudhari, and B. Zhou, "Acoustic modeling with bootstrap and restructuring for low-resourced languages," in Proc. Interspeech, 2010, pp. 2974-2977.
16. L. R. Bahl, F. Jelinek, and R. L. Mercer, "A maximum likelihood approach to continuous speech recognition," IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-5, no. 2, pp. 179-190, Feb. 1983. (Pubitemid 13555897)
17. Y. Normandin, "Hidden Markov models, maximum mutual information estimation and the speech recognition problem," Ph.D dissertation, McGill Univ., Montreal, QC, Canada, 1991.
18. 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.
19. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D dissertation, Univ. of Cambridge, Cambridge, U.K., 2003.
20. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 257-286, Feb. 1989.
21. P. Bühlmann and B. Yu, "Analyzing bagging," Ann. Statist., vol. 30, no. 4, pp. 927-961, 2002. (Pubitemid 37095335)
22. F. Zaman and H. Hirose, "Effect of subsampling rate on subbagging and related ensembles of stable classifiers," in Proc. Int. Conf. Pattern Recogn. Mach. Intell., 2009, pp. 44-49.
23. A. Elisseeff, T. Evgeniou, and M. Pontil, "Stability of randomized learning algorithms," J. Mach. Learn. Res., vol. 6, pp. 55-79, 2005.
24. X. Liu and M. Gales, "Automatic model complexity control using marginalized discriminative growth functions," IEEE Trans. Audio, Speech, Lang. Process., vol. 15, no. 4, pp. 1414-1424, May 2007.
25. M. Padmanabhan and L. R. Bahl, "Model complexity adaptation using a discriminant measure," IEEE Trans. Speech Audio Process., vol. 8, no. 2, pp. 205-208, Mar. 2000. (Pubitemid 30578375)
26. G. F. G. Yared, F. Violaro, and L. C. Sousa, "Gaussian elimination algorithm for HMM complexity reduction in continuous speech recognition systems," in Proc. Interspeech, 2005, pp. 377-380. (Pubitemid 43908078)
27. K. Shinoda and T. Watanabe, "Speaker adaptation with autonomous model complexity control by MDL principle," in Proc. Int. Conf. Acoust., Speech, Signal Process., 1995, pp. 717-720.
28. X. He and Y. Zhao, "Model complexity optimization for nonnative English speakers," in Proc. Interspeech, 2001, pp. 1461-1464.
29. C. Hennig, "Methods for merging gaussian mixture components," Adv. Data Anal. Classific., vol. 4, no. 1, pp. 3-34, 2010.
30. O. Bellot, D. Matrouf, P. Nocera, G. Linares, and J.-F. Bonastre, "Structural speaker adaptation using maximum a posteriori approach and a Gaussian distributions merging technique," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2003, pp. 121-124.
31. W. Xu, J. Duchateau, K. Demuynck, and I. Dologlou, "A new approach to merging Gaussian densities in large vocabulary continuous speech recognition," in Proc. IEEE Benelux Signal Process. Symp., 1998, pp. 231-234.
32. S. Kullback, Information Theory and Statistics. New York: Wiley, 1959.
33. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York: Wiley, 2001.
34. X. Chen, X. Cui, J. Xue, P. A. Olsen, J. R. Hershey, and B. Zhou, "Full covariance bootstrapped acoustic model clustering," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2011, pp. 4496-4499.
35. P. L. Dognin, J. R. Hershey, V. Goel, and P. A. Olsen, "Refactoring acoustic models using variational density approximation," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2009, pp. 4473-4476.
36. P. L. Dognin, J. R. Hershey, V. Goel, and P. A. Olsen, "Refactoring acoustic models using variational Expectation-Maximization," in Proc. Interspeech, 2009, pp. 212-215.
37. J. M. Hammersley and D. C. Handscomb, Monte Carlo Methods. London, U.K.: Methuen, 1975.
38. G. S. Fishman, Monte Carlo: Concepts, Algorithms, and Applications. New York: Springer, 1995.
39. R. Y. Rubinstein and D. P. Kroese, Simulation and the Mont Carlo Method, 2nd ed. New York: Wiley, 2007.
40. 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.
41. X. Cui, X. Chen, J. Xue, P. A. Olsen, J. R. Hershey, and B. Zhou, "Acoustic modeling with bootstrap and restructuring based on full covariance," in Proc. Interspeech, 2011, pp. 1697-1700.
42. J. R. Hershey and P. A. Olsen, "Variational Bhattacharyya divergence for hidden Markov models," in Proc. Int. Conf. Acoust., Speech, Signal Process., 2008, pp. 4557-4560.
43. G. Saon, D. Povey, and G. Zweig, "Anatomy of an extremely fast LVCSR decoder," in Proc. Interspeech, 2005, pp. 549-552. (Pubitemid 43908121)
44. P. S. Gopalakrishnan, D. Kotievsky, A. Nadas, D. Nahanloo, and M. A. Pichieny, "Decoder selection based on cross-entropies," in Int. Conf. Acoust., Speech, Signal Process., 1988, pp. 20-23.