A STUDY OF SPEAKER ADAPTATION BASED ON MINIMUM CLASSIFICATION ERROR TRAINING

4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Volumn , Issue , 1995, Pages 81-84

  Matsui, Tomoko ^a   Furui, Sadaoki ^a  

^a NTT CORPORATION   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ERRORS; PARAMETER ESTIMATION; SPEECH COMMUNICATION; SPEECH RECOGNITION;

ADAPTATION METHODS; HIDDEN-MARKOV MODELS; MAXIMUM A POSTERIORI; MAXIMUM A POSTERIORI ESTIMATION; MAXIMUM-A-POSTERIORI ESTIMATIONS; MINIMUM CLASSIFICATION ERROR TRAINING; MODELING PARAMETERS; PERFORMANCE; RECOGNITION ERROR; SPEAKER ADAPTATION;

HIDDEN MARKOV MODELS;

EID: 3643088089     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. C.-H. Lee and J.L. Gauvain, " Speaker adaptation based on MAP estimation of HMM parameters, " Proc. ICASSP, Minneapolis, pp. 11-558-561, 1993.
2. J.L. Gauvain and C.-H. Lee, "Maximum a posteriori estimation for multivariate gaussian mixture observations of Markov chains," IEEE Trans. Speech and Audio Processing, Vol. 2, No. 2, pp.291-298, 1994.
3. C.H. Lin, P.-C. Chang, and C.-H. Wu, "An ini¬tial study on speaker adaptation for Mandarin syllable recognition with minimum error discrim¬inative training," Proc. ICSLP, Yokohama, pp. 1-307-310, 1994.
4. C.-H. Lee, C.-H. Lin and B.-H. Juang, "A study on speaker adaptation of the parameters of con¬tinuous density hidden Markov models," IEEE Trans, on ASSP, April, 1991.
5. C.-S. Liu, C.-H. Lee, and W. Chou, "A study on minimum error discriminative training for speaker recognition," J. Acoust. Soc. Amer., 97, 1, pp. 637-648, 1995.
6. B.-H. Juang and S. Katagiri, "Discriminative training," J. Acoust. Soc. Jpn., 13, 6, pp. 333-339, 1992.
7. W. Chou, B.-H. Juang, and C.-H. Lee, "Segmen¬tal GPD training of HMM based speech recog¬nizer," Proc. ICASSP, San Francisco, pp.1-473-476, 1992