A framework for Anticipatory Machine Improvisation and Style Imitation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

A framework for Anticipatory Machine Improvisation and Style Imitation

Abstract

We present a first step towards anticipatory machine improvisation systems. The proposed system, based on fundamentals of music cognition, is a multi-agent memory-based collaborative and competitive reinforcement learning architecture, capable of live interaction with a musician or a music score. Results demonstrate the ability to model long-term stylistic planning and need for much less training data than reported in previous works.
Fichier principal
Vignette du fichier
paper_abials06_2.pdf (421.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00839074 , version 1 (27-06-2013)

Identifiers

  • HAL Id : hal-00839074 , version 1

Cite

Arshia Cont, Shlomo Dubnov, Gerard Assayag. A framework for Anticipatory Machine Improvisation and Style Imitation. Anticipatory Behavior in Adaptive Learning Systems (ABiALS), 2006, Rome, Italy. ⟨hal-00839074⟩
92 View
378 Download

Share

Gmail Facebook X LinkedIn More