Rapid online adaptation using speaker space model evolution

Speech Communication

Volumn 42, Issue 3-4, 2004, Pages 467-478

  Kim, Dong Kook ^a,b,c   Kim, Nam Soo ^b  

^a Electronics and Telecommunications Research Institute (ETRI)   (South Korea)

^b Seoul National University   (South Korea)

^c Chonnam National University   (South Korea)

Author keywords

Latent variable model; Online adaptation; Prior evolution; Quasi Bayes estimate; Rapid speaker adaptation; Speaker space model

Indexed keywords

DATA REDUCTION; DATABASE SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PRINCIPAL COMPONENT ANALYSIS;

LATENT VARIABLE MODELS; ONLINE ADAPTATION; PRIOR EVOLUTION; QUASI-BAYES ESTIMATE; RAPID SPEAKER ADAPTATION; SPEAKER SPACE MODELS;

SPEECH RECOGNITION;

EID: 1842580255     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2004.01.002     Document Type: Article

References (28)

1. Botterweck, H., 2001. Anisotropic MAP defined by eigenvoice for large vocabulary speech recognition. In: Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Salt Lake City, USA.
2. Chen, K.-T., Wang, H.-M., 2001. Eigenspace-based maximum a posteriori linear regression for rapid speaker adaptation. In: Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., Salt Lake City, USA.
3. Chen, K.-T., Liau, W.-W., Wang H.-M., Lee, L.-S., 2000. Fast speaker adaptation using eigenspace-based maximum likelihood linear regression. In: Proc. Internat. Conf. Spoken Language Process., Beijing, China, pp. 742-745.
4. Chien J.-T. On-line hierarchical transformation of hidden Markov models for speech recognition. IEEE Trans. Speech Audio Process. 7:1999;656-667.
5. Chien J.-T. Quasi-Bayes linear regression for sequential learning of hidden Markov models. IEEE Trans. Speech Audio Process. 10(July):2002;268-278.
6. Chou, W., 1999. Maximum a posteriori linear regression with elliptically symmetric matrix priors. In: Proc. Euro. Conf. Speech Comm. Technol., pp. 1-4.
7. Dempster A.P., Laird N.M., Rubin D.B. Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Statist. Soc. 39:1977;1-38.
8. Gales M.J.F. Cluster adaptive training of hidden Markov models. IEEE Trans. Speech Audio Process. 8(4):2000;417-428.
9. Gauvain J.L., Lee C.-H. Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 2:1994;291-298.
10. Huo Q., Lee C.-H. On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate. IEEE Trans. Speech Audio Process. 5:1997;161-172.
11. Huo Q., Lee C.-H. On-line adaptive learning of the correlated continuous density hidden Markov models for speech recognition. IEEE Trans. Speech Audio Process. 6:1998;386-397.
12. Huo Q., Ma B. Online adaptive learning of continuous-density hidden Markov models based on multiple-stream prior evolution and posterior pooling. IEEE Trans. Speech Audio Process. 9:2001;388-398.
13. Jolliffe I.T. Principal Component Analysis. 1986;Springer-Verlag.
14. Kim, D.K., Kim, N.S., 2000. Bayesian speaker adaptation based on probabilistic principal component analysis. In: Proc. Internat. Conf. Spoken Language Process., pp. 734-737.
15. Kim, D.K., Kim, N.S., 2001. Maximum a posteriori adaptation of HMM parameters based on probabilistic principal component analysis. In: Adaptation Methods for Speech Recognition, ISCA ITR-Workshop, Sophia-Antipolis, France, pp. 25-28.
16. Kim, D.K., Kim, N.S., 2002. Online adaptation of continuous density hidden Markov models based on speaker space model evolution. In: Proc. Internat. Conf. Spoken Language Process., Denver, USA, pp. 1393-1396.
17. Kim D.K., Kim N.S. Maximum a posteriori adaptation of HMM parameters based on speaker space projection. Speech Commun. 42:2004;59-73.
18. Kim, D.K., Kim, Y.J., Lim, W.H., Kim, N.S., 2003. Online adaptation using transformation space model evolution. In: Proc. IEEE Internat. Conf. Acoust. Speech Signal Process., pp. 304-307.
19. Kuhn R., Junqua J.-C., Nguyen P., Niedzielski N. Rapid speaker adaptation in eigenvoice space. IEEE Trans. Speech Audio Process. 8(6):2000;695-707.
20. Kuhn, R., Perronnin, F., Junqua, J.-C., 2001. Time is money: why very rapid adaptation matters. In: Adaptation Methods for Speech Recognition. ISCA ITR-Workshop, Sophia-Antipolis, France, pp. 33-36.
21. Lee C.-H. On stochastic feature and model compensation approaches to robust speech recognition. Speech Comm. 25:1997;29-47.
22. Lee C.-H., Huo Q. On adaptive decision rules and decision parameter adaptation for automatic speech recognition. Proc. IEEE. 88(8):2000;1241-1269.
23. Leggetter C.J., Woodland P.C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Comput. Speech Lang. 9:1995;171-185.
24. Rubin D., Thayer D. EM algorithms for factor analysis. Psychometrika. 47:1982;69-76.
25. Tipping M., Bishop C. Mixtures of probabilistic principal component analysers. Neural Comput. 11(2):1999;443-482.
26. Woodland, P.C., 2001. Speaker adaptation for continuous density HMMs; a review. In: Adaptation Methods for Speech Recognition, ISCA ITR-Workshop, Sophia-Antipolis, France, pp. 11-19.
27. Young, S.J., Odell, J.J., Woodland, P.C., 1994. Tree-based state tying for high accuracy acoustic modelling. In: Proc. ARPA Human Language Tech. Workshop, Vol. 1, pp. 286-291.
28. Zavaliagkos, G., 1995. Maximum a posteriori adaptation techniques for speech recognition. Ph.D. dissertation, Northeastern Univ., Boston.