Algorithmic Clustering of Music

TL;DR

This paper introduces a universal, compression-based music classification method that requires no prior domain knowledge, effectively distinguishing musical genres and clustering by composer using information theory principles.

Contribution

It presents a novel, domain-agnostic clustering approach based on Kolmogorov complexity and information distance, applicable across diverse fields.

Findings

Successfully distinguishes musical genres

Clusters pieces by composer

Operates without domain-specific knowledge

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.