A neural network for composer classification - Archive ouverte HAL Access content directly
Poster Communications Year : 2018

A neural network for composer classification


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 (393.02 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

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




  • HAL Id : hal-01879276 , version 1


Gianluca Micchi. A neural network for composer classification. International Society for Music Information Retrieval Conference (ISMIR 2018), 2018, Paris, France. ⟨hal-01879276⟩
358 View
1125 Download


Gmail Facebook X LinkedIn More