Pachet, F., Westermann, G. and Laigre, D Musical Data Mining for Electronic Music Distribution. Proceedings of the 1st WedelMusic Conference, pages 101-106, Firenze, Italy, 2001

Sony CSL authors: Damien Laigre, François Pachet, Gert Westermann

Abstract

Music classification is a key ingredient for electronic music distribution. Because of the lack of standards in music classification – or the lack of enforcement of existing standards – there is a huge amount of unclassified titles of music in the world. In this paper we propose a method of classification based on musical data mining techniques that uses co-occurrence and correlation analysis for classification. This method allows for the rapid extraction of similarities between musical titles or artists. We investigate the usability of radio playlists and compilation CD databases for our data mining technique, and we compare the generated results with human similarity judgments. Based on a clustering technique, we show that interesting clusters can reveal specific music genres and allow classifying titles of music in a kind of objective manner.

Keywords: Cuidado, data mining, music similarity, classification

Downloads

[PDF] Adobe Acrobat PDF file

BibTeX entry

@INPROCEEDINGS { pachet:01c, ADDRESS="Firenze, Italy", AUTHOR="Pachet, F. and Westermann, G. and Laigre, D", BOOKTITLE="Proceedings of the 1st WedelMusic Conference", PAGES="101-106", TITLE="Musical Data Mining for Electronic Music Distribution", YEAR="2001", }