musique contemporaine

Ircam - articles scientifiques notice originale

An Adaptive System for Music Classification and Tagging

Type

text
 

Genre(s)

article
 

Forme(s)

document imprimé
 

Cette ressource est disponible chez l'organisme suivant : Ircam - Centre Pompidou

Identification

Titre

An Adaptive System for Music Classification and Tagging
 

Nom(s)

Burred, Juan José (auteur)
 
Peeters, Geoffroy (auteur)
 

Publication

Graz, Autriche , 2009
 

Description

Sujet(s)

Music Information Retrieval   music classification   music indexing   music tagging   multilabel classification   Support Vector Machines
 

Résumé

We present a system that can learn effective classification models from music databases of very different characteristics, including both single-label collections indexed by genre or artist and multilabel databases of musical mood and instrumentation, where multiple tags can be applied to each track. Adaptability is attained by means of automatic feature and model selection, both embedded in the multiple-instance binary relevance learning of a Support Vector Machine. We discuss strategies for compensating overfitting and unbalanced training sets.
 

Note(s)

Contribution au colloque ou congrès : International Workshop on Learning the Semantics of Audio Signals (LSAS)
 

Localisation

Envoyer la notice

Bookmark and Share 
 

Identifiant OAI

 

Date de la notice

2009-10-09 02:00:00
 

Identifiant portail

 

Contact