Keyword spotting using supervised/unsupervised competitive learning

Author

Tadj, Chakib ; Poirier, Franck

Author_Institution

Signal Dept., Telecom Paris, France

Volume

1

fYear

1995

fDate

9-12 May 1995

Firstpage

301

Abstract

We present a novel hybrid keyword spotting system that combines supervised and unsupervised competitive learning algorithms. The first stage is a SOFM (self-organizing feature maps) module which is specifically designed for discriminating between keywords (KWs) and non-keywords (NKWs). The second stage is a FDVQ (fuzzy dynamic vector quantization) module which consists of discriminating between KWs detected by the first stage processing. The results show an improvement of about 9% on the accuracy of the system comparing to our standard one

Keywords

learning (artificial intelligence); modules; self-organising feature maps; speech recognition; unsupervised learning; vector quantisation; SOFM; fuzzy dynamic vector quantization; hybrid keyword spotting system; learning algorithms; modules; self-organizing feature maps; supervised competitive learning; system accuracy; unsupervised competitive learning; Automatic speech recognition; Computer networks; Context modeling; Ear; Hidden Markov models; Large-scale systems; Nearest neighbor searches; Power system modeling; Speech recognition; Telecommunications; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on

Conference_Location

Detroit, MI

ISSN

1520-6149

Print_ISBN

0-7803-2431-5

Type

conf

DOI

10.1109/ICASSP.1995.479533

Filename

479533