Speech recognition based on a model of human auditory system

Author

Koizumi, Takuya ; Mori, Mikio ; Taniguchi, Shuji

Author_Institution

Dept. of Inf. Sci., Fukui Univ., Japan

Volume

2

fYear

1996

fDate

3-6 Oct 1996

Firstpage

937

Abstract

The paper deals with a new phoneme recognition system based on a model of human auditory system. This system is made up of a model of the human cochlea and a simple multilayer recurrent neural network which has feedback connections of self-loop type. The ability of this system has been investigated by a phoneme recognition experiment using a number of Japanese words uttered by a native male speaker. The result of the experiment shows that recognition accuracies achieved with this system in the presence of noise are higher than those obtained by a combination of frequency spectral analysis by DFT and a conventional feedforward neural network and that the cochlea model effectively prevents deterioration due to noise of recognition accuracy

Keywords

discrete Fourier transforms; ear; feedforward neural nets; hearing; multilayer perceptrons; physiological models; recurrent neural nets; spectral analysis; speech recognition; Japanese words; feedforward neural network; frequency spectral analysis; human auditory system model; human cochlea; multilayer recurrent neural network; native male speaker; noise; phoneme recognition system; recognition accuracies; self-loop type feedback connections; speech recognition; Auditory system; Feedforward neural networks; Frequency; Humans; Multi-layer neural network; Neural networks; Neurofeedback; Recurrent neural networks; Spectral analysis; Speech recognition;

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.1996.607756

Filename

607756