A combined self-organizing feature map and multilayer perceptron for isolated word recognition

Author

Kuang, Z. ; Kuh, Anthony

Author_Institution

Dragon Systems Inc., Newton, MA, USA

Volume

40

Issue

11

fYear

1992

fDate

11/1/1992 12:00:00 AM

Firstpage

2651

Lastpage

2657

Abstract

A neural network system which combines a self-organizing feature map and multilayer perception for the problem of isolated word speech recognition is presented. A new method combining self-organization learning and K-means clustering is used for the training of the feature map, and an efficient adaptive nearby-search coding method based on the `locality´ of the self-organization is designed. The coding method is shown to save about 50% computation without degradation in recognition rate compared to full-search coding. Various experiments for different choices of parameters in the system were conducted on the TI 20 word database with best recognition rates as high as 99.5% for both speaker-dependent and multispeaker-dependent tests

Keywords

feedforward neural nets; self-organising feature maps; speech recognition; K-means clustering; adaptive nearby-search coding method; feedforward network; isolated word recognition; multilayer perceptron; multispeaker-dependent tests; neural network; self-organization learning; self-organizing feature map; speaker dependent tests; speech recognition; training; Acoustic noise; Degradation; Design methodology; Multi-layer neural network; Multilayer perceptrons; Neural networks; Speech enhancement; Speech processing; Speech recognition; Vocabulary;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.165652

Filename

165652