Musical Genre Classification Enhanced by Improved Source Separation Technique

Abstract

We present a system for musical genre classification based on audio features extracted from signals which correspond to distinct musical instrument sources. For the separation of the musical sources, we propose an innovative technique in which the convolutive sparse coding algorithm is applied to several portions of the audio signal. The system is evaluated and its performance is assessed.

Extracted Key Phrases

8 Figures and Tables

Cite this paper

@inproceedings{Lampropoulos2005MusicalGC, title={Musical Genre Classification Enhanced by Improved Source Separation Technique}, author={Aristomenis S. Lampropoulos and Paraskevi S. Lampropoulou and George A. Tsihrintzis}, booktitle={ISMIR}, year={2005} }