Correctness-adjusted unsupervised discriminative acoustic model adaptation

IEEE Transactions on Audio, Speech and Language Processing

Volumn 20, Issue 10, 2012, Pages 2648-2656

  Gibson, Matthew ^a   Hain, Thomas ^a  

^a UNIVERSITY OF SHEFFIELD   (United Kingdom)

Author keywords

Discriminative; domain adaptation; MPE; SVM; unsupervised speaker adaptation

Indexed keywords

DISCRIMINATIVE; DOMAIN ADAPTATION; MPE; SVM; UNSUPERVISED SPEAKER ADAPTATION;

SPEECH RECOGNITION; SUPPORT VECTOR MACHINES;

TRANSCRIPTION;

EID: 84867152087     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2012.2209420     Document Type: Article

References (29)

1. C. J. Leggetter and P. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Comput. Speech Lang., vol. 9, no. 2, pp. 171-185, 1995.
2. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Cambridge Univ., Cambridge, U.K., 2003.
3. D. Povey, M. Gales, D. Y. Kim, and P. Woodland, "MMI-MAP and MPE-MAP for acoustic model adaptation," in Proc. Eurospeech, Geneva, Switzerland, 2003, pp. 1981-1984.
4. D. Povey, P. Woodland, and M. Gales, "Discriminative MAP for acoustic model adaptation," in Proc. ICASSP, Hong Kong, 2003, pp. 312-315.
5. A. Gunawardana and W. Byrne, "Discriminative speaker adaptation with conditional maximum likelihood linear regression," in Proc. Eurospeech, Aalborg, Denmark, 2001, pp. 1203-1206.
6. J.Wu and Q. Huo, "Supervised adaptation of MCE-trained CDHMMS using minimum classification error linear regression," in Proc. ICASSP, Orlando, 2002, pp. 605-608.
7. L. Wang and P. Woodland, "MPE-based discriminative linear transform for speaker adaptation," in Proc. ICASSP,Montreal, QC, Canada, 2004, pp. 321-324.
8. S. Tsakalidis, V. Doumpiotis, and W. Byrne, "Discriminative linear transforms for feature normalization and speaker adaptation in HMM estimation," in Proc. ICSLP, Denver, CO, 2002, pp. 2585-2588.
9. L.Wang and P.Woodland, "Discriminative adaptive training using the MPE criterion," in Proc. ASRU, Virgin Islands, 2002, pp. 279-284.
10. K. Yu and M. J. F. Gales, "Discriminative cluster adaptive training," IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 5, pp. 1694-1703, Sep. 2006.
11. S. Young, G. Evermann, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland, The HTK Book for HTK Version 3.2.1. Cambridge, U.K.: Cambridge Univ. Eng. Dept., 2003.
12. D. Povey and P. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, Orlando, FL, 2002, pp. 105-108.
13. M. Gibson and T. Hain, "Error approximation and minimum phone error acoustic model estimation," IEEE Trans. Speech Audio Process., vol. 18, no. 2, pp. 1269-1279, Feb. 2010.
14. L. Wang and P. Woodland, "MPE-based discriminative linear transforms for speaker adaptation," Comput. Speech Lang., vol. 22, no. 3, pp. 256-272, 2008.
15. M. Pitz, F. Wessel, and H. Ney, "Improved MLLR speaker adaptation using confidence measures for conversational speech recognition," in Proc. ICSLP, 2000, vol. 4, pp. 548-551.
16. F. Wessel, R. Schlüter, K. Macherey, and H. Ney, "Confidence measures for large vocabulary continuous speech recognition," IEEE Trans. Speech Audio Process., vol. 9, no. 3, pp. 288-298, 2001.
17. G. Evermann and P.Woodland, "Large vocabulary decoding and confidence estimation using word posterior probabilities," in Proc. ICASSP 2000, 2000, vol. 3, pp. 1655-1658.
18. M. Gibson and T. Hain, Confidence-Informed Unsupervised Minimum Bayes Risk Acoustic Model Adaptation Sheffield Univ. Dept. of Comput. Sci., 2011, Tech. Rep. CS-11-01.
19. R. Zhang and A. Rudnicky, "Word level confidence annotation using combinations of features," in Proc. Eur. Conf. Speech Commun. Technol., 2001, pp. 2105-2108.
20. T. Joachims, Advances in Kernel Methods-Support Vector Learning, B. Schölkopf, C. Burges, and A. Smola, Eds. Cambridge, MA: MIT Press, 1999.
21. T. Joachims and C.-N. Yu, "Sparse Kernel SVMs via cutting-plane training," in Proc. Eur. Conf. Mach. Learn. (ECML), Mach. Learn. J., Spec. ECML Iss., 2009, vol. 76, pp. 179-193.
22. P. Woodland, M. Gales, D. Pye, and S. Young, "Broadcast news transcription using HTK," in Proc. ICASSP, Munich, 1997, vol. 2, pp. 719-722.
23. B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol. 6, pp. 1304-1312, 1974.
24. S. Young, J. Odell, and P. Woodland, "Tree-based state tying for high accuracy acoustic modelling," in Proc. ARPA Workshop Human Lang. Technol., Plainsboro, NJ, 1994, pp. 307-312.
25. S. Fitt, "Documentation and User Guide to UNISYN Lexicon and Post-Lexical Rules," Tech. Rep. : Edinburgh Univ., Centre for Speech Technol. Res., 2000.
26. M. Weintraub, F. Beaufays, Z. Rivlin, Y. Konig, and A. Stolcke, "Neural-network based measures of confidence for word recognition," in Proc. ICASSP, 1997, pp. 887-890.
27. L. Gillick and S. Cox, "Some statistical issues in the comparison of speech recognition algorithms," in Proc. ICASSP, Philadelphia, PA, 1989, pp. 532-535.
28. D. S. Pallett, W. M. Fisher, and J. Fiscus, "Tools for the analysis of benchmark speech recognition tests," in Proc. ICASSP, Albuquerque, NM, 1990, pp. 97-100.
29. C. Cieri, D. Miller, and K. Walker, "The Fisher corpus: A resource for the next generations of speech-to-text," in Proc. 4th Int. Conf. Lang. Resources Eval. (LREC), 2004, p. 69.