A fast algorithm for music search by similarity in large databases based on modified Symetrized Kullback Leibler Divergence

Christophe Charbuillet, Geoffroy Peeters, Stanislav Barton, Valerie Gouet-Brunet

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

State of the art on music similarity search is based on the pairwise comparison of statistical models representing audio features. The comparison is often obtained by the Symetrized Kullback-Leibler Divergence (SKLD). When dealing with very large databases (over one million items), usual search by similarity algorithms - sequential or exhaustive search - cannot be used. In these cases, optimized search strategies such as the M-tree reduces the search time but requires the dissimilarity measure to be a metric. Unfortunately, this is not the case of the SKLD. In this paper, we propose and successfully test on a large-scale a modification of the Symetrized Kullback-Leibler Divergence which allows to use it as a metric.

Original languageEnglish
Title of host publicationCBMI 2010 - 8th International Workshop on Content-Based Multimedia Indexing
Pages19-24
Number of pages6
DOIs
Publication statusPublished - 20 Sept 2010
Externally publishedYes
Event8th International Workshop on Content-Based Multimedia Indexing, CBMI 2010 - Grenoble, France
Duration: 23 Jun 201025 Jun 2010

Publication series

NameProceedings - International Workshop on Content-Based Multimedia Indexing
ISSN (Print)1949-3991

Conference

Conference8th International Workshop on Content-Based Multimedia Indexing, CBMI 2010
Country/TerritoryFrance
CityGrenoble
Period23/06/1025/06/10

Fingerprint

Dive into the research topics of 'A fast algorithm for music search by similarity in large databases based on modified Symetrized Kullback Leibler Divergence'. Together they form a unique fingerprint.

Cite this