PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Algorithmic clustering of music
Rudi Cilibrasi, Paul M.B. Vitanyi and Ronald de Wolf
Computer Music Journal Volume 2004, Number To appear, 2004.

Abstract

We present a fully automatic method for music classification, based only on compression of strings that represent the music pieces. The method uses no background knowledge about music whatsoever: It is completely general and can, without change, be used in different areas like linguistic classification and genomics. It is based on an ideal theory of the information content in individual objects (Kolmogorov complexity), information distance, and a universal similarity metric. Experiments show that the method distinguishes reasonably well between various musical genres and can even cluster pieces by composer.

EPrint Type:Article
Additional Information:This paper generated wide media attention: * Software to unzip identity of unknown composers, New Scientist, 12 April 2003, by Hazel Muir; see for local copy here. This is about our music clustering work reported in R. Cilibrasi, R. de Wolf, P. Vitanyi, Algorithmic clustering of music, Submitted. This work is also reported by * Software sorts tunes, Technology Research News, April 23/30, 2003, by Kimberly Patch , see for local copy here. Also in Unzipping composers and musical style, by Fred "zAmboni" Locklear, Ars Technica 4/10/2003 * In France Classer musiques, langues, images, textes et genomes, Pour La Science, 317(March 2004), 98--103, by Jean-Paul Delahaye , (Pour la Science = Edition francaise de Scientific American); for the full article see a local copy here * in the Netherlands: o De afstand tussen Haendel en Hendrix, by Rob van den Berg, NRC-Handelsblad, O&W Bijlage, April 26, 2003; and o Zip-programma ontmaskert componist, Intermediair, April 24, 2003. * In Russia by Izvestia newspaper; * In Italy by Neural: revista di cultura dei nuova media .hactivism .emusic .new media art no 20, glu 2003; * In Europe Research Consortium News by ERCIM News No. 54, July 2003 * In Mexico by Cerebral Dynamics Bulletin; * in Australia by ABC Radio in Newcastle; * in Germany by Deutschland Funk, April 28, 2003. * In Austria by Kurier Zeitung, May 6, 2003
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Learning/Statistics & Optimisation
Multimodal Integration
ID Code:129
Deposited By:Paul Vitányi
Deposited On:27 May 2004