Title :
Speech/music discrimination using awarped LPC-based feature and a fuzzy expert system for intelligent audio coding
Author :
Munoz-Exposito, J.E. ; Garcia-Galan, S. ; Ruiz-Reyes, N. ; Vera-Candeas, P. ; Rivas-Pena, F.
Author_Institution :
Electron. & Telecommun. Eng. Dept., Univ. of Jaen, Linares, Spain
Abstract :
Automatic discrimination of speech and music is an important tool in many multimedia applications. This paper presents an evolutionary fuzzy rules-based speech/music discrimination approach for intelligent audio coding. A low complexity but effective feature, called Warped LPC-based Spectral Centroid (WLPC-SC), is defined for the analysis stage of the discrimination system. The final decision is made by a fuzzy expert system, which improves the accuracy rate provided by a Gaussian Mixture Model (GMM) classifier taking into account the audio labels assigned by the GMM classifier to past audio frames. Comparison between WLPC-SC and most timbral features proposed in [8] is performed, aiming to assess the good discriminatory power of the proposed feature. The accuracy rate improvement due to the fuzzy expert system is also reported. Experimental results reveal that our speech/music discriminator is robust and fast, making it suitable for intelligent audio coding.
Keywords :
Gaussian processes; audio coding; evolutionary computation; expert systems; fuzzy systems; linear predictive coding; mixture models; music; GMM classifier; Gaussian mixture model classifier; WLPC-SC; fuzzy expert system; intelligent audio coding; multimedia applications; music discrimination; speech discrimination; warped LPC-based spectral centroid; Abstracts; Accuracy; Europe; Iron; Mel frequency cepstral coefficient; Multiple signal classification; Speech;
Conference_Titel :
Signal Processing Conference, 2006 14th European
Conference_Location :
Florence