Title :
A speech/music discriminator using RMS and zero-crossings
Author :
Panagiotakis, C. ; Tziritas, G.
Author_Institution :
Dept. of Comput. Sci., Univ. of Crete, Heraklion, Greece
Abstract :
An audio segmentation method and a speech/music classifier are proposed. The characteristics used are considerably reduced. Segmentation is based on mean signal amplitude distribution, whereas classification utilizes an additional characteristic related to the mean frequency. The segmentation and classification algorithms were benchmarked on a large data set, with correct segmentation about 97% of the time and correct classification about 95%.
Keywords :
audio signal processing; mean square error methods; signal classification; speech processing; RMS; audio segmentation method; mean frequency; mean signal amplitυde distribυtion; root mean square method; speech-music classification; speech-music discriminator; zero-crossing; Abstracts; Estimation; Histograms; Robustness; Speech; World Wide Web;
Conference_Titel :
Signal Processing Conference, 2002 11th European
Conference_Location :
Toulouse
