Skip to Main content Skip to Navigation
Conference papers

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
Document type :
Conference papers
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/hal-00839072
Contributor : Arshia Cont <>
Submitted on : Thursday, June 27, 2013 - 10:48:33 AM
Last modification on : Tuesday, July 13, 2021 - 2:17:00 PM
Long-term archiving on: : Saturday, September 28, 2013 - 4:16:07 AM

File

AudioOracle_5.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00839072, version 1

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. ⟨hal-00839072⟩

Share

Metrics

Record views

476

Files downloads

692