A neural network for composer classification

Gianluca Micchi 1, 2
2 Algomus
MIS - Modélisation, Information & Systèmes, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : 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.
Type de document :
Poster
International Society for Music Information Retrieval Conference (ISMIR 2018), 2018, Paris, France
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01879276
Contributeur : Mathieu Giraud <>
Soumis le : samedi 22 septembre 2018 - 19:17:46
Dernière modification le : mardi 2 octobre 2018 - 13:35:04

Fichier

2018-ismir-lb-composer.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

  • HAL Id : hal-01879276, version 1

Collections

Citation

Gianluca Micchi. A neural network for composer classification. International Society for Music Information Retrieval Conference (ISMIR 2018), 2018, Paris, France. 〈hal-01879276〉

Partager

Métriques

Consultations de la notice

56

Téléchargements de fichiers

13