Maximum entropy models capture melodic styles

Abstract : We introduce a Maximum Entropy model able to capture the statistics of melodies in music. The model can be used to generate new melodies that emulate the style of a given musical corpus. Instead of using the n–body interactions of (n−1)–order Markov models, traditionally used in automatic music generation, we use a k-nearest neighbour model with pairwise interactions only. In that way, we keep the number of parameters low and avoid over-fitting problems typical of Markov models. We show that long-range musical phrases don’t need to be explicitly enforced using high-order Markov interactions, but can instead emerge from multiple, competing, pairwise interactions. We validate our Maximum Entropy model by contrasting how much the generated sequences capture the style of the original corpus without plagiarizing it. To this end we use a data-compression approach to discriminate the levels of borrowing and innovation featured by the artificial sequences. Our modelling scheme outperforms both fixed-order and variable-order Markov models. This shows that, despite being based only on pairwise interactions, our scheme opens the possibility to generate musically sensible alterations of the original phrases, providing a way to generate innovation.
Type de document :
Article dans une revue
Scientific Reports, Nature Publishing Group, 2017, 7, pp.9172. 〈10.1038/s41598-017-08028-4〉
Liste complète des métadonnées

Littérature citée [22 références]  Voir  Masquer  Télécharger

http://hal.upmc.fr/hal-01585581
Contributeur : Gestionnaire Hal-Upmc <>
Soumis le : lundi 11 septembre 2017 - 16:26:38
Dernière modification le : jeudi 11 janvier 2018 - 06:27:15

Fichier

s41598-017-08028-4.pdf
Publication financée par une institution

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Collections

Citation

Jason Sakellariou, Francesca Tria, Vittorio Loreto, Francois Pachet. Maximum entropy models capture melodic styles. Scientific Reports, Nature Publishing Group, 2017, 7, pp.9172. 〈10.1038/s41598-017-08028-4〉. 〈hal-01585581〉

Partager

Métriques

Consultations de la notice

113

Téléchargements de fichiers

26