A neural network for composer classification - HAL Accéder directement au contenu
Poster de conférence Année : 2018

A neural network for composer classification

Résumé

I present a neural network approach to automatically extract musical features from 20-second audio clips in order to predict their composer. The network is composed of three convolutional layers followed by a long short-term memory recurrent layer. The model reaches an accuracy of 70% on the validation set when classifying amongst 6 composers. The work represents the early stage of a project devoted to automatic feature detection and visualization.
Fichier principal
Vignette du fichier
2018-ismir-lb-composer.pdf ( 393.01 Ko ) Télécharger
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01879276, version 1 (22-09-2018)

Licence

Paternité - CC BY 4.0

Identifiants

  • HAL Id : hal-01879276 , version 1

Citer

Gianluca Micchi. A neural network for composer classification. International Society for Music Information Retrieval Conference (ISMIR 2018), 2018, Paris, France. ⟨hal-01879276⟩
362 Consultations
1137 Téléchargements
Dernière date de mise à jour le 07/04/2024
comment ces indicateurs sont-ils produits

Partager

Gmail Facebook Twitter LinkedIn Plus