Continuous speech recognition for the TIMIT database using neural networks

Author

Fallside, F. ; Lucke, H. ; Marsland, T.P. ; O´Shea, P.J. ; Owen, M. St J ; Prager, R.W. ; Robinson, A.J. ; Russell, N.H.

Author_Institution

Dept. of Eng., Cambridge Univ., UK

fYear

1990

fDate

3-6 Apr 1990

Firstpage

445

Abstract

Four types of neural networks which have previously been established for speech recognition and tested on a small, seven-speaker, 100-sentence database are applied to the TIMIT database. The networks are a recurrent network phoneme recognizer, a modified Kanerva model morph recognizer, a compositional representation phoneme-to-word recognizer, and a modified Kanerva model morph-to-word recognizer. The major result is for the recurrent net, giving a phoneme recognition accuracy of 57% from the si and sx sentences. The Kanerva morph recognizer achieves 66.2% accuracy for a small subset of the sa and sx sentences. The results for the word recognizers are incomplete

Keywords

neural nets; speech recognition; Kanerva morph recognizer; compositional representation phoneme-to-word recognizer; continuous speech recognition; modified Kanerva model morph recognizer; modified Kanerva model morph-to-word recognizer; neural networks; phoneme recognition accuracy; recurrent network phoneme recognizer; Data engineering; Databases; Hidden Markov models; Management training; Neural networks; Packaging; Recurrent neural networks; Speech recognition; Testing; 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.1990.115745

Filename

115745