Using Multidimensional Sequences For Improvisation In The OMax Paradigm

Ken Déguernel 1, 2 Emmanuel Vincent 1 Gérard Assayag 2
1 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 Repmus - Représentations musicales
STMS - Sciences et Technologies de la Musique et du Son
Abstract : Automatic music improvisation systems based on the OMax paradigm use training over a one-dimensional sequence to generate original improvisations. Different systems use different heuristics to guide the improvisation but none of these benefits from training over a multidimensional sequence. We propose a system creating improvisation in a closer way to a human improviser where the intuition of a context is enriched with knowledge. This system combines a probabilistic model taking into account the multidimen-sional aspect of music trained on a corpus, with a factor oracle. The probabilistic model is constructed by interpolating sub-models and represents the knowledge of the system, while the factor oracle (structure used in OMax) represents the context. The results show the potential of such a system to perform better navigation in the factor oracle, guided by the knowledge on several dimensions.
Liste complète des métadonnées

Cited literature [21 references]  Display  Hide  Download

https://hal.inria.fr/hal-01346797
Contributor : Ken Déguernel <>
Submitted on : Tuesday, July 19, 2016 - 4:00:20 PM
Last modification on : Wednesday, April 3, 2019 - 1:23:02 AM

File

Using Multidimensional Sequenc...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01346797, version 1

Citation

Ken Déguernel, Emmanuel Vincent, Gérard Assayag. Using Multidimensional Sequences For Improvisation In The OMax Paradigm. 13th Sound and Music Computing Conference, Aug 2016, Hamburg, Germany. ⟨hal-01346797⟩

Share

Metrics

Record views

735

Files downloads

256