Some phonetic recognition experiments using artificial neural nets

Author

Leung, Hong C. ; Zue, Victor W.

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., MIT, Cambridge, MA, USA

fYear

1988

fDate

11-14 Apr 1988

Firstpage

422

Abstract

This paper is concerned with the application of artificial neural nets to phonetic recognition. The goal is to investigate how the framework of multilayer perceptrons can be exploited in speech recognition when the are augmented with acoustic-phonetic knowledge. Major issues as the choice of the error metric, the use of contextual information, and determination of the training procedure are investigated within a set of experiments that attempt to recognize the 16 vowels in American English. The results, based on some 10000 vowel tokens excised from 1000 sentences spoken by 200 speakers, indicate that a top-choice accuracy of 54% and 67% can be achieved for the context-independent and -dependent networks, respectively

Keywords

neural nets; speech recognition; American English; acoustic-phonetic knowledge; artificial neural nets; context dependent networks; context independent networks; contextual information; error metric; multilayer perceptrons; phonetic recognition experiments; speech recognition; training procedure; vowel tokens; Artificial neural networks; Character recognition; Feature extraction; Frequency; Laboratories; Multilayer perceptrons; Neural networks; Signal processing; Speech processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.196608

Filename

196608