Integration of Heteroscedastic Linear Discriminant Analysis (HLDA) into adaptive training

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2006, Pages

  Stemmer, Georg ^a   Brugnara, Fabio ^b  

^a SIEMENS AG   (Germany)

^b ITC IRST   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE SYSTEMS; ALGORITHMS; DISCRIMINANT ANALYSIS; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD; WORD PROCESSING;

HETEROSCEDASTIC LINEAR DISCRIMINANT ANALYSIS (HLDA); SPEAKER-SPECIFIC TRANSFORMATIONS; WORD ERROR RATE (WER);

SPEECH RECOGNITION;

EID: 33947687744     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. N. Kumar and A.G. Andreou, "Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition," Speech Communication, vol. 26, pp. 283-297, 1998.
2. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training," in Proc. ICSLP, 1996, pp. 1137-1140.
3. L. Lee and R.C. Rose, "Speaker normalization using efficient frequency warping procedures," in Proc. ICASSP, 1996, pp. 353-356.
4. C.J. Leggetter and P.C. Woodland, "Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models," Computer Speech and Language, vol. 9, pp. 171-185, 1995.
5. M.J.F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition," Computer Speech and Language, vol. 12, pp. 75-98, 1998.
6. V.V. Digalakis, D. Rtischev, and L.G. Neumeyer, "Speaker adaptation using constrained estimation of Gaussian mixtures," IEEE Transactions on Speech and Audio Processing, vol. 3, no. 5, pp. 357-366, 1995.
7. D. Giuliani, M. Gerosa, and E Brugnara, "Speaker normalization through constrained MLLR based transforms," in Proc. ICSLP, 2004, vol. 4, pp. 2893-2897.
8. G. Stemmer, F. Brugnara, and D. Giuliani, "Adaptive training using simple target models," in Proc. ICASSP, 2005, vol. 1, pp. 997-1000.
9. S. Matsoukas and R. Schwartz, "Improved speaker adaptation using speaker dependent feature projections," in IEEE ASRU Workshop, 2003, pp. 273-278.
10. M.J.F. Gales, "Semi-tied covariance matrices for hidden Markov models," IEEE Transactions on Speech and Audio Processing, vol. 7, pp. 272-281, 1999.
11. G. Stemmer, "Heteroscedastic linear discriminant analysis (HLDA) - derivation, implementation and integration into adaptive training," Tech. Rep. T05-09-02, ITC-irst, 2005.
12. G. Stemmer, V. Zeissler, C. Hacker, E. Nöth, and H. Niemann, "A phone recognizer helps to recognize words better," in Proc. ICASSP, 2003, vol. 1, pp. 736-739.