Improved maximum model distance for HMM training

Electronics Letters

Volumn 35, Issue 10, 1999, Pages 783-785

  He, Q H ^a   Kwong, S ^b   Man, K F ^b   Tang, K S ^b  

^a SOUTH CHINA UNIVERSITY OF TECHNOLOGY   (China)

^b CITY UNIVERSITY OF HONG KONG   (Hong Kong)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; MATHEMATICAL MODELS; SPEECH ANALYSIS;

IMPROVED MAXIMUM MODEL DISTANCE (IMMD) APPROACH;

SPEECH RECOGNITION;

EID: 0032660823     PISSN: 00135194     EISSN: None     Source Type: Journal    
DOI: 10.1049/el:19990550     Document Type: Article

References (5)

1. BAHL, R., BROWN, P.F., DE SOUZA, P.V., and MERCER, R.L.: 'Maximum mutual information estimation of hidden Markov model parameters for speech recognition', Proc. 1986 IEEE Int. Conf. Acoustics, Speech, and Signal Processing, Tokyo, Japan, 1986, pp. 49-52
2. EPHRAIM, Y., DEMBO, A., and RABINER, L.R.: 'A minimum discrimination information approach for hidden Markov modeling', IEEE Trans., 1989, IT-35, (5), pp. 1001-1003
3. CHOU, W., LEE, C.H., JUANG, B.H., and SOONG, F.K.: 'A minimum error rate pattern recognition approach to speech recognition', Int. J. Pattern Recogn. Artificial Intelligence, 1994, 8, (1), pp. 5-31
4. EPHRAIM, Y., and RABINER, L.R.: 'On the relations between modelling approaches for speech recognition', IEEE Trans., 1990, IT-36, (2), pp. 372-380
5. KWONG, S., HE, Q.H., MAN, K.F., and TANG, K.S.: 'A maximum model distance approach for HMM-based speech recognition', Pattern Recognition, 1998, 31, (3), pp. 219-229