Mixture splitting technique and temporal control in a HMM-based recognition system

Author

Montacié, C. ; Caratay, M.-J. ; Barras, C.

Author_Institution

Paris VI Univ., France

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

977

Abstract

Studies various techniques to improve the performance and to reduce the computation cost and the required memory of a speech recognition system based on hidden Markov models (HMMs). For the efficiency of the system, we first study the optimization of the number of HMM parameters according to training data. We experiment with the temporal control of the phonetic transitions on a lexical decoding task with a significant 5% improvement. Finally, a preliminary method for dynamically selecting a sublexicon is studied in order to reduce the lexical decoding cost

Keywords

Gaussian distribution; decoding; hidden Markov models; optimisation; software performance evaluation; speech recognition; HMM parameter optimization; computation cost; dynamic sublexicon selection; efficiency; hidden Markov models; lexical decoding cost; lexical decoding task; mixture splitting technique; performance; phonetic transitions; required memory; speech recognition system; temporal control; training data; Computational efficiency; Control systems; Costs; Databases; Decoding; Frequency estimation; Gaussian distribution; Hidden Markov models; Probability density function; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on

Conference_Location

Philadelphia, PA

Print_ISBN

0-7803-3555-4

Type

conf

DOI

10.1109/ICSLP.1996.607766

Filename

607766