Title :
Wavelet-FILVQ classifier for speech analysis
Author :
Scheunders, Paul
Abstract :
This paper describes a novel speech signal classification scheme based on spectrograms which are subjected to wavelet transform: a procedure which yields specific information regarding time and frequency variation of the signal. Feature vectors are extracted and classified using LVQ networks. The output of the network is interpreted as a fuzzy membership coefficient. This scheme is applied to the classification of voice dysphonia
Keywords :
fuzzy neural nets; feature vector extraction; frequency variation; fuzzy membership coefficient; learning vector quantisation network; spectrograms; speech signal classification; time variation; voice dysphonia classification; wavelet transform; Feature extraction; Fuzzy sets; Hospitals; Neural networks; Spectrogram; Speech analysis; Speech recognition; Time frequency analysis; Wavelet analysis; Wavelet transforms;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.547418
