Title :
Keyword spotting using supervised/unsupervised competitive learning
Author :
Tadj, Chakib ; Poirier, Franck
Author_Institution :
Signal Dept., Telecom Paris, France
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;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2431-5
DOI :
10.1109/ICASSP.1995.479533
