An Adaptive System for Music Classification and Tagging - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

An Adaptive System for Music Classification and Tagging

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.
Fichier non déposé

Dates et versions

hal-01106472 , version 1 (20-01-2015)

Identifiants

  • HAL Id : hal-01106472 , version 1

Citer

Juan Jose Burred, Geoffroy Peeters. An Adaptive System for Music Classification and Tagging. International Workshop on Learning the Semantics of Audio Signals (LSAS), Dec 2009, Graz, Autriche. ⟨hal-01106472⟩
102 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More