Audio Oracle: A New Algorithm for Fast Learning of Audio Structures

Abstract : In this paper we present a new method for indexing of audio data in terms of repeating sub-clips of variable length that we call audio factors. The new structure allows fast retrieval and recombination of sub-clips in a manner that assures continuity between splice points. The resulting structure accomplishes effectively a new method for texture synthesis, where the amount of innovation is controlled by one of the synthesis parameters. In the paper we present the new structure and describe the algorithms for efficiently computing the different indexing links. Examples of texture synthesis are provided in the paper.
Keywords : Computer music
Type de document :
Communication dans un congrès
Proceedings of International Computer Music Conference (ICMC), 2007, Copenhagen, Denmark. ICMA, 2007
Liste complète des métadonnées

Littérature citée [9 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00839072
Contributeur : Arshia Cont <>
Soumis le : jeudi 27 juin 2013 - 10:48:33
Dernière modification le : vendredi 31 août 2018 - 09:14:29
Document(s) archivé(s) le : samedi 28 septembre 2013 - 04:16:07

Fichier

AudioOracle_5.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00839072, version 1

Collections

Citation

Shlomo Dubnov, Gerard Assayag, Arshia Cont. Audio Oracle: A New Algorithm for Fast Learning of Audio Structures. Proceedings of International Computer Music Conference (ICMC), 2007, Copenhagen, Denmark. ICMA, 2007. 〈hal-00839072〉

Partager

Métriques

Consultations de la notice

344

Téléchargements de fichiers

255