USING SIMULATED ANNEALING EXPECTATION MAXIMIZATION ALGORITHM FOR HIDDEN MARKOV MODEL PARAMETERS ESTIMATION

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 449-452

  Simonin, J ^a   Mokbel, C ^a  

^a ORANGE LABS   (France)

Author keywords

[No Author keywords available]

Indexed keywords

IMAGE SEGMENTATION; MAXIMUM PRINCIPLE; PARAMETER ESTIMATION; SIMULATED ANNEALING; SPEECH COMMUNICATION; SPEECH RECOGNITION;

EXPECTATION-MAXIMIZATION METHOD; EXPECTATIONS MAXIMIZATION ALGORITHMS; HIDDEN-MARKOV MODELS; LOCAL OPTIMA; MODEL PARAMETER ESTIMATION; PARAMETERS ESTIMATION; SIMULATED ANNEALING TECHNIQUES; SPEECH RECOGNITION SYSTEMS; TRAINING DATA; VITERBI;

HIDDEN MARKOV MODELS;

EID: 61549112632     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.21437/eurospeech.1997-155     Document Type: Conference Paper

References (6)

1. A.P. Dempster, N.M. Laird & D.B. Rubin, "Maximum Likelihood from incomplete data via the EM algorithm", JRSS, B39: 1-38, 1977.
2. S. Kirkpatrick, CD. Gelatt & M.P. Vecchi, "Optimization by simulated annealing", Science, Vol. 220:671-680, 1983.
3. R. De Mori, M. Galler & F. Brugnara, "Search and learning strategies for improving hidden Markov models". Computer Speech and Language, Vol. 9: 107-121, 1995.
4. J. Simonin, S. Bodin, D. Jouvet & K. Bartkova, "Parameter tying for flexible speech recognition", Proc. oflCSLP, Vol. 2: 1089-1092, 1996.
5. G. Celeux & J. Diebolt, "A simulated annealing type EM algorithm", Rapport de recherche INRIA, No 1123: 1-24, 1989.
6. L. Rabiner & B.H. Juang, "Fundamentals of speech recognition", Prentice Hall Signal Processing Series, 1993.