International Symposium on Chinese Spoken Language Processing (ISCSLP 2002)

Taipei, Taiwan
August 23-24, 2002

Speech Detection Based on Discrete Wavelet Transform

Ching-Tang Hsieh, Chih-Hsu Hsu

(1) Tamkang University, Taipei, Taiwan
(2) Dahan Institute of Technology, Hua-Lien, Taiwan

This paper presents a fuzzy system to discriminate speech signals from background. In our previous works, we had developed a method for speech classification. For speech classification, the universe of discourse is divided into two types, and each type is treated as a class. These are background and speech signals. The rectangular fuzzy system (RES) is used to classify frames and integrate the rule-based approach. The variance of first detail and the third approximation can extract fuzzy classification rules. Experimental results demonstrate the superior performance to the conventional ones. The effectiveness of the proposed system is confirmed by the experimental results.

Full Paper

Bibliographic reference.  Hsieh, Ching-Tang / Hsu, Chih-Hsu (2002): "Speech detection based on discrete wavelet transform", In ISCSLP 2002, paper 106.