ROBUST HMM TO VARIATION OF NOISY ENVIRONMENTS BASED ON VARIANCE EXTENSION OF NOISE MODELS

6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Volumn , Issue , 1999, Pages 2387-2390

  Matsumoto, Hiroshi ^a   Ubukata, Hiroaki ^a  

^a SHINSHU UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH COMMUNICATION; SPEECH RECOGNITION;

CEPSTRAL COEFFICIENTS; DIGIT RECOGNITION; LOW ORDER; NOISE DATA; NOISE MODELS; NOISY ENVIRONMENT; PARALLEL MODEL COMBINATIONS; SNR MISMATCH; SPEAKER INDEPENDENTS; VARIANCE EXPANSION;

SIGNAL TO NOISE RATIO;

EID: 0011400310     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (5)

1. Gales N.J. and Young S.J.,"An improved approach to the hidden markovl model decomposition of speech and noise," Proceedings of ICASSP, pp.232-236, 1992.
2. Martine F., Shikano K., Minami Y., and Okabe Y., "Recognition of noisy speech by composition of hidden Markov models," IEICE Technical Report, SP92-96, pp.9-16, 1992.
3. Davis S.B. and Mermelstein P., "Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences," IEEE Transactions ASSP, Vol.28, pp.357-366, 1980.
4. Varga A.P., Steeneken H.J.M., Tomlinson M. and Jones D., "The NOISEX-92 study on the effect of additive noise on automatic speech recognition," Tech. Rep., DRA Speech Res. Unit, 1992.
5. Itahashi S.,"Recent Speech Database Projects in Japan," Proceedings of ICSLP, pp.1081-1084, 1990.