Improved training and recognition algorithms with VQ-based hidden Markov models

Author

Falkhausen, M. ; Euler, S.A. ; Wolf, D.

Author_Institution

Inst. fur Angewandte Phys., Frankfurt Univ., West Germany

fYear

1990

fDate

3-6 Apr 1990

Firstpage

549

Abstract

Two aspects of the application of vector quantization (VQ) in speaker-independent isolated-word recognition using discrete hidden Markov models (HMMs) are discussed. An automatic segmentation scheme using the information about the sequence of the L nearest codebook entries to a feature vector is presented. Based on the resulting segment boundaries, the parameters of the word models are estimated. A smoothing of the symbol probabilities is discussed. In the calculation of the model probabilities, the probability for the best codebook index is replaced by a weighted sum over the R best codebook indices. The algorithms were tested on a speaker-independent German database for a vocabulary with 23 words, and results are presented

Keywords

Markov processes; encoding; learning systems; probability; speech recognition; German database; codebook index; hidden Markov models; segmentation; speaker-independent isolated-word recognition; speech recognition; symbol probabilities; vector quantization; word models; Automatic speech recognition; Automatic testing; Databases; Frequency; Hidden Markov models; Probability; Smoothing methods; System testing; Testing; Vector quantization; Viterbi algorithm; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115771

Filename

115771