Hidden Markov models estimation via the most informative stopping times for Viterbi algorithm

Author

Kogan, Joseph A.

Author_Institution

Courant Inst. of Math. Sci., New York Univ., NY, USA

fYear

1995

fDate

17-22 Sep 1995

Firstpage

178

Abstract

We propose a sequential approach for studying the Viterbi algorithm via a renewal sequence of the most informative stopping times which allows us in particular to obtain new asymptotic “single-letter” decoding conditions of equivalency between the Baum-Welch, segmental K-means and vector quantization algorithms of the hidden Markov models parameters estimation which have important applications in speech recognition

Keywords

decoding; hidden Markov models; maximum likelihood estimation; parameter estimation; sequential estimation; speech recognition; vector quantisation; Baum-Welch algorithm; Viterbi algorithm; asymptotic single-letter decoding; hidden Markov models estimation; most informative stopping times; parameters estimation; renewal sequence; segmental K-means algorithm; sequential approach; speech recognition; vector quantization algorithm; Decoding; Distortion measurement; Dynamic programming; Entropy; Hidden Markov models; Parameter estimation; Sequential analysis; Speech recognition; Vector quantization; Viterbi algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Theory, 1995. Proceedings., 1995 IEEE International Symposium on

Conference_Location

Whistler, BC

Print_ISBN

0-7803-2453-6

Type

conf

DOI

10.1109/ISIT.1995.531527

Filename

531527