Comparison of different techniques on Thai speech recognition

Author

Ahkuputra, Visarut ; Jitapunkul, Somchai ; Maneenoi, Ekkarit ; Kasuriya, Sawit ; Amornkul, Phakapong

Author_Institution

Digital Signal Process. Res. Lab., Chulalongkorn Univ., Bangkok, Thailand

fYear

1998

fDate

24-27 Nov 1998

Firstpage

177

Lastpage

180

Abstract

This paper introduces the comparison between Thai isolated word speech recognition techniques using the Hidden Markov Model, the Modified Backpropagation Neural Network, and the Fuzzy-Neural Network. The recognition has been made on the ten isolated Thai numerals from zero to nine under the same system configuration for all the approaches. The 15-state left-to-right discrete hidden Markov model in cooperation with the vector quantization technique was compared with the multilayer network using error backpropagation, the modified backpropagation, and also with the fuzzy-neural network with the same configuration. The recognition accuracy using hidden Markov model, neural network, modified neural network and fuzzy-neural network approaches are 84.250 percent, 73.030 percent, 78.000 percent, and 78.300 percent respectively

Keywords

backpropagation; fuzzy neural nets; hidden Markov models; speech recognition; vector quantisation; Thai speech recognition; discrete HMM; error backpropagation; fuzzy neural network; hidden Markov model; isolated word speech recognition; modified backpropagation neural network; multilayer network; recognition accuracy; vector quantization technique; Backpropagation algorithms; Clustering algorithms; Digital signal processing; Hidden Markov models; Multi-layer neural network; Multilayer perceptrons; Natural languages; Neural networks; Speech recognition; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1998. IEEE APCCAS 1998. The 1998 IEEE Asia-Pacific Conference on

Conference_Location

Chiangmai

Print_ISBN

0-7803-5146-0

Type

conf

DOI

10.1109/APCCAS.1998.743705

Filename

743705