musique contemporaine

Ircam - articles scientifiques notice originale

Anticipatory Model of Musical Style Imitation using Collaborative and Competitive Reinforcement Learning

Type

text
 

Genre(s)

article
 

Forme(s)

document numérique
 

Cette ressource est disponible chez l'organisme suivant : Ircam - Centre Pompidou

Identification

Titre

Anticipatory Model of Musical Style Imitation using Collaborative and Competitive Reinforcement Learning
 

Nom(s)

Cont, Arshia (auteur)
 
Dubnov, Shlomo (auteur)
 
Assayag, Gérard (auteur)
 

Publication

Berlin, Germany , Martin Butz and Olivier Sigaud and Gianluca Baldassarre, 2007
 

Description

Sujet(s)

Style   Anticipation   Machine Learning
 

Résumé

The role of expectation in listening and composing music has drawn much attention in music cognition since about half a century ago. In this paper, we provide a first attempt to model some aspects of musical expectation specifically pertained to short-time and working memories, in an anticipatory framework. In our proposal Anticipation is the mental realization of possible predicted actions and their effect on the perception of the world at an instant in time. We demonstrate the model in applications to automatic improvisation and style imitation. The proposed model,based on cognitive foundations of musical expectation, is an active model using reinforcement learning techniques with multiple agents that learn competitively and in collaboration. We show that compared to similar models, this anticipatory framework needs little training data and demonstrate complex musical behavior such as long-term planning and formal shapes as a result of the anticipatory architecture. We provide sample results and discuss further research.
 

Note(s)

Article paru dans : Anticipatory Behavior in Adaptive Learning Systems
 

Localisation

Envoyer la notice

Bookmark and Share 
 

Identifiant OAI

 

Date de la notice

2010-02-25 01:00:00
 

Identifiant portail

 

Contact