Authors:
Shahrokh Ghaemmaghami
1
and
Jalil Shirazi
2
Affiliations:
1
Sharif University of Technology, Iran, Islamic Republic of
;
2
Islamic Azad University, Iran, Islamic Republic of
Keyword(s):
Audio classification, sinusoidal model.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Audio and Speech Processing
;
Digital Signal Processing
;
Multimedia
;
Multimedia Signal Processing
;
Pattern Recognition
;
Software Engineering
;
Telecommunications
Abstract:
In this paper, a new feature set for audio classification is presented and evaluated based on sinusoidal modeling of audio signals. Variance of the birth-death frequencies in sinusoidal model of signal, as a measure of harmony, is used and compared to typical features as the input into an audio classifier. The performance of this sinusoidal model feature is evaluated through classification of audio to speech and music using both the GMM and the SVM classifiers. Classification results show that the proposed feature is quite successful in speech/music classification. Experimental comparisons with popular features for audio classification, such as HZCRR and LSTER, are presented and discussed. By using a set of three features, we achieved 96.83% accuracy, in one-sec segment based audio classification.