Title :
Speech/Audio Signal Classification Using Spectral Flux Pattern Recognition
Author :
Sangkil Lee ; Jieun Kim ; Insung Lee
Author_Institution :
Dept. of Radio & Commun., Chungbuk Nat. Univ., Cheongju, South Korea
Abstract :
In this paper, we present a novel method for the improvement of speech and audio signal classification using spectral flux (SF) pattern recognition for the MPEG Unified Speech and Audio Coding (USAC) standard. For effective pattern recognition, the Gaussian mixture model (GMM)probability model is used. For the optimal GMM parameter extraction, we use the expectation maximization (EM)algorithm. The proposed classification algorithm is divided into two significant parts. The first one extracts the optimal parameters for the GMM. The second distinguishes between speech and audio signals using SF pattern recognition. The performance of the proposed classification algorithm shows better results compared to the conventionally implemented USAC scheme.
Keywords :
Gaussian processes; audio coding; expectation-maximisation algorithm; signal classification; speech coding; EM algorithm; GMM parameter extraction; GMM probability model; Gaussian mixture model; MPEG USAC standard; MPEG unified speech and audio coding standard; SF pattern recognition; expectation maximization algorithm; spectral flux pattern recognition; speech-audio signal classification; Buffer storage; Classification algorithms; Pattern classification; Speech; Speech coding; Speech recognition; Audio coding; Classification algorithms; Pattern recognition; Spectral analysis; Speech coding;
Conference_Titel :
Signal Processing Systems (SiPS), 2012 IEEE Workshop on
Conference_Location :
Quebec City, QC
Print_ISBN :
978-1-4673-2986-6
DOI :
10.1109/SiPS.2012.36
