A dynamic in-search data selection method with its applications to acoustic modeling and utterance verification

IEEE Transactions on Speech and Audio Processing

Volumn 13, Issue 5, 2005, Pages 945-955

  Jiang, Hui ^a,b   Soong, Frank K ^a,c,e,f   Lee, Chin Hui ^a,d,g,h,i  

^a IEEE   (Canada)

^b YORK UNIVERSITY   (Canada)

^c MICROSOFT RESEARCH ASIA   (China)

^d GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

^e CHINESE UNIVERSITY OF HONG KONG   (Hong Kong)

^f CUHK MSRA Joint Research Laboratory

^g GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

^h European Speech Communication Association   (United States)

ⁱ NONE   (Taiwan)

Author keywords

Competing token; Discriminative training; In search data selection; Log likelihood ratio (LLR) testing; Sequential maximum a posteriori (MAP) adaptation; True token (TT)

Indexed keywords

COMPETING TOKEN; DISCRIMINATIVE TRAINING; IN-SERACH DATA SELECTION; LOG LOKELIHOOD RATIO (LLR) TESTING; SEQUENTIAL MAXIMUM A POSTERIORI (MAP) ADAPTATION; TRUE TOKEN (TT);

ERROR ANALYSIS; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY; SEARCH ENGINES;

DATA REDUCTION;

EID: 27644444018     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2005.851947     Document Type: Article

References (26)

1. T. Anastasakos, J. McDonough, R. Schwarts, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. Int. Conf. Spoken Language Processing, 1996, pp. 1137-1140.
2. L. Arslan and J. Hansen, "Selective training for hidden Markov models with applications to speech classification," IEEE Trans. Speech Audio Process., vol. 7, no. 1, pp. 46-54, Jan. 1999.
3. 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. ICASSP, Tokyo, Japan, 1986, pp. 49-52.
4. M. DeGroot, Optimal Statistical Decisions. New York: McGraw-Hill, 1970.
5. M. J. F. Gales, "Cluster adaptive training for speech recognition," in Proc. Int. Conf. Spoken Language Processing, Sydney, Australia, 1998, pp. 1783-1786.
6. M. J. F. Gales, "Cluster adaptive training of hidden Markobv models," IEEE Trans. Speech Audio Process., vol. 8, no. 4, pp. 417-428, Jul. 2000.
7. Y. Gao, B. Ramabhadran, and M. Picheny, "New adaptation techniques for large vocabulary continuous speech recognition," presented at the ISCA ITRW Workshop, Paris, France, Sep. 2000.
8. J.-L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate Gaussian mixture observation of Markov chains," IEEE Trans. Speech Audio Process., vol. 2, no. 2, pp. 291-298, Mar. 1994.
9. Q. Huo and C.-H. Lee, "On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate," IEEE Trans. Speech Audio Process., vol. 5, no. 2, pp. 161-172, Mar. 1997.
10. Q. Huo and B. Ma, "Irrelevant variability normalization in learning structure from data: a case study on decision-tree based HMM state tying," in Proc. ICASSP, May 1999, pp. 577-580.
11. H. Jiang and L. Deng, "A robust training strategy against extraneous acoustic variations for spontaneous speech recognition," in Proc. 6th Int. Conf. Spoken Language Processing, Beijing, China, Oct. 2000, pp. IV-161-IV-164.
12. H. Jiang, F. Soong, and C.-H. Lee, "A data selection strategy for utterance verification in continuous speech recognition," in Proc. EUROSPEECH, Sep. 2001, pp. 2573-2576.
13. H. Jiang and L. Deng, "A robust compensation strategy for extraneous acoustic variations in spontaneous speech recognition," IEEE Trans. Speech Audio Process., vol. 10, no. 1, pp. 9-17, Jan. 2002.
14. H. Jiang, O. Siohan, F. Soong, and C.-H. Lee, "A dynamic in-search discriminative training approach for large vocabulary speech recognition," presented at the ICASSP, Orlando, FL, May 2002.
15. H. Jiang, "Confidence measures for speech recognition: A survey," Speech Commun., vol. 45, pp. 455-470, 2005.
16. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error training," IEEE Trans. Signal Process., vol. 40, no. 12, pp. 3043-3054, Dec. 1992.
17. B.-H. Juang, W. Chou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Trans. Speech Audio Process., vol. 5, no. 3, pp. 257-265, May 1997.
18. C.-H. Lee, "A tutorial on speaker and speech verification," in Proc. NORSIG, Vigso, Denmark, Jun. 1998, pp. 9-16.
19. R. Sukkar and C.-H. Lee, "Vocabulary independent discriminative utterance verification for nonkeyword rejection in subword based speech recognition," IEEE Trans. Speech Audio Process., vol. 4, no. 6, pp. 420-429, Nov. 1996.
20. R. Sukkar, A. Setlur, M. Rahim, and C.-H. Lee, "Utterance verification of keyword strings using word based minimum verification error (WB-MVE) training," in Proc. ICASSP, Atlanta, GA, May 1996, pp. 516-519.
21. R. Sukkar, A. R. Setlur, C.-H. Lee, and J. Jacob, "Verifying and correcting string hypotheses using discriminative utterance verification," Speech Commun., vol. 22, pp. 333-342, 1997.
22. M. G. Rahim, C.-H. Lee, and B.-H. Juang, "Discriminant utterance verification for connected digits recognition," IEEE Trans. Speech Audio Process., vol. 5, no. 3, pp. 266-277, May 1997.
23. W. Reichl and W. Chou, "Robust decision tree state tying for continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 8, no. 5, pp. 555-566, Sep. 2000.
24. S. J. Young, J. J. Odell, and P. C. Woodland, "Tree-based state tying for high accuracy acoustic modeling," in Proc. ARPA Human Language Technology Workshop, 1994, pp. 307-312.
25. F. Wessel et al., "Confidence measures for large vocabulary continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 9, no. 3, pp. 288-298, Mar. 2001.
26. P. C. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models for speech recognition," Comput. Speech Lang., vol. 16, no. 1, pp. 25-47, Jan. 2002.