Music genre classification based on ensemble of signals produced by source separation methods

Abstract

In this paper, we present a system for musical genre classification that uses a preprocessing module to separate corresponding audio signals into three source signals. A feature extraction procedure is applied to each separated signal and the extracted features are fed into an ensemble combination of Support Vector Machine-based classifiers for genre classification. For the source separation task, we examine and compare two relevant algorithms, namely Convolutive Sparse Coding and a Wavelet Packets-based algorithm. We evaluate our system on a music database of four hundred music samples from four different music genres. Experimental results show that there is a higher classification accuracy in applying a source separation algorithm before feature extraction.