Unsupervised acoustic model adaptation based on ensemble methods

IEEE Journal on Selected Topics in Signal Processing

Volumn 4, Issue 6, 2010, Pages 1007-1015

  Shinozaki, Takahiro ^a   Kubota, Yu ^a   Furui, Sadaoki ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Acoustic model; cross validation; ensemble methods; speech recognition; unsupervised adaptation

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODEL ADAPTATION; ADAPTATION ALGORITHMS; ADAPTATION FRAMEWORK; COMPUTATIONAL COSTS; CROSS VALIDATION; ENSEMBLE METHODS; LINEAR REGRESSION METHODS; NOISY SPEECH RECOGNITION; RELATIVE REDUCTION; SPEECH RECOGNITION PERFORMANCE; UNSUPERVISED ADAPTATION; WORD ERROR RATE;

ALGORITHMS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION;

SPEECH RECOGNITION;

EID: 78649249806     PISSN: 19324553     EISSN: None     Source Type: Journal    
DOI: 10.1109/JSTSP.2010.2076010     Document Type: Article

References (30)

1. M. Gales and S. Young, "The application of hidden Markov models in speech recognition," Foundat. Trends Signal Process., vol. 1, no. 3, pp. 195-304, 2008.
2. S. Nakagawa, T. Watanabe, H. nishizaki, and T. Utsuro, "An unsuper-vised speaker adaptation method for lecture-style spontaneous speech recognition using multiple recognition systems," IEICE Trans. Inf. Syst., vol. E88-D, no. 3, pp. 463-471, 2005.
3. P. A. Devijver and J. Kittler, Pattern Recognition: A Statistical Approach. London, U.K.: Prentice-Hall, 1982.
4. L. Breiman, "Bagging predictors," Mach. Learn., vol. 24, no. 2, pp. 123-140, 1996.
5. T. Shinozaki, Y. Kubota, and S. Furui, "Unsupervised cross-validation adaptation algorithms for improved adaptation performance," in Proc. ICASSP, 2009, pp. 4377-4380.
6. N. S. Kim and C. K. Un, "Deleted strategy for MMI-based HMM training," IEEE Trans. Speech Audio Process., vol. 6, no. 3, pp. 299-303, May 1998.
7. T. Shinozaki and M. Ostendorf, "Cross-validation and aggregated EM training for robust parameter estimation," Comput. Speech Lang., vol. 22, no. 2, pp. 185-195, 2008.
8. T. Shinozaki and T. Kawahara, "GMM and HMM training by aggregated EM algorithm with increased ensemble sizes for robust parameter estimation," in Proc. ICASSP, 2008, pp. 4405-4408.
9. Machine Learning Ensemble,' [Online] Available: http://en. wikipedia.org/wiki/Machine-learning-ensemble Jun. 2009
10. C. J. Leggetter and P. C. Woodland, "Flexible speaker adaptation using maximum likelihood linear regression," in Proc. Eurospeech, 1995, pp. 1155-1158.
11. J. Gauvain and C. Lee, "Maximum a posteriori estimation for multi-variate Gaussian mixture observations of Markov chains," IEEE Trans. Speech Audio Process., vol. 2, no. 2, pp. 291-298, Apr. 1994.
12. A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Statist. Soc., no. 1, pp. 1-38, 1977, Series B 39.
13. H. Soltau, B. Kingsbury, L. Mangu, D. Povery, G. Saon, and G. Zweig, "The IBM 2004 conversational telephony system for rich transcription," in Proc. ICASSP, 2005, vol. I, pp. 205-208.
14. J. G. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction rover," in Proc. IEEE ASRU, 1997, pp. 347-352.
15. G. Evermann and P. C. Woodland, "Posterior probability decoding, confidence estimation and system combination," in Proc. Speech Transcript. Workshop, 2000.
16. T. Kawahara, H. Nanjo, T. Shinozaki, and S. Furui, "Benchmark test for speech recognition using the Corpus of spontaneous Japanese," in Proc. SSPR2003, 2003, pp. 135-138.
17. K. Itou, M. Yamamoto, K. Takeda, T. Takezawa, T. Matsuoka, T. Kobayashi, K. Shikano, and S. Itahashi, "JNAS: Japanese speech corpus for large vocabulary continuous speech recognition research," Acoust Soc. Jpn. E, vol. 20, no. 3, pp. 199-206, 1999.
18. D. Povey and P. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002, vol. I, pp. 105-108.
19. S. Davis and P. Mermelstein, "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," IEEE Trans. Acoust. Speech, Signal Process., vol. 28, no. 4, pp. 357-366, Aug. 1980.
20. H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," J. Acoust. Soc. Amer., vol. 87, no. 4, pp. 1738-1752, 1990.
21. S. Furui, "Speaker-independent isolated word recognition using dynamic features of speech spectrum," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-34, no. 1, pp. 52-59, Feb. 1986.
22. T. Kato, J. Okamoto, and M. Shozakai, "Physical parameter analysis of Japanese speech at automobile driving act, and analysis of correlation between the parameter and accuracy," in Autumn Meeting Acoust. Soc. Jpn. (in Japanese), 2007, vol. 3-Q-25, pp. 267-268.
23. S. Itahashi, "On recent speech corpora activities in japan," J. Acoust. Soc. Jpn. (E), vol. 20, no. 3, pp. 163-169, 1999.
24. S. F. Boll, "Suppression of acoustic noise in speech using spectral subtraction," IEEE Trans. Acoust., Speech, Signal Process., vol. ASSP-27, no. 2, pp. 113-120, Apr. 1979.
25. P. R. Dixon, D. A. Caseiro, T. Oonishi, and S. Furui, "The TITECH large vocabulary WFST speech recognition system," in Proc. IEEE ASRU, 2007, pp. 443-448.
26. A. Lee, T. Kawahara, and S. Doshita, "An efficient two-pass search algorithm using word trellis index," in Proc. ICSLP, 1998, pp. 1831-1834.
27. S. Young et al., The HTK Book. Cambridge, U.K.: Cambridge Univ. Eng. Dept., 2005.
28. L. Gillick and S. Cox, "Some statistical issues in the comparison of speech recognition algorithms," in Proc. ICASSP, vol. 89, pp. 532-535.
29. H. Jiang, "Confidence measures for speech recognition: A survey," Speech Commun., vol. 45, no. 4, pp. 455-470, 2005.
30. L. Lamel, J. Gauvain, and G. Adda, "Investigating lightly supervised acoustic model training," in Proc. ICASSP, 2001, vol. 1, pp. 477-480.