Skip to Main content Skip to Navigation
Master thesis

Découverte automatique de structures musicales en temps réel par la géométrie de l'information

Vincent Lostanlen 1, 2, *
* Corresponding author
1 MuTant - Synchronous Realtime Processing and Programming of Music Signals
IRCAM - Institut de Recherche et Coordination Acoustique/Musique, Inria Paris-Rocquencourt, UPMC - Université Pierre et Marie Curie - Paris 6, CNRS - Centre National de la Recherche Scientifique
Abstract : This master's thesis aims at exploring the challenge of automatically retrieving musical structures within an audio file. Our main contribution is to formulate this well-studied problem in the frame- work of computational information geometry, an emerging field at the frontier between statistics, differential geometry, and data mining. In this framework, we unify the fundamental tasks of event segmentation and similarity computing in a single sequential scheme for structure discovery. Furthermore, we propose an original metric on temporal segments, which combines several criteria of geometrical comparability : divergence between centroids, as well as inclusion and intersection ratios of corresponding information balls.
Complete list of metadata

Cited literature [56 references]  Display  Hide  Download

https://hal.inria.fr/hal-00849736
Contributor : Arshia Cont <>
Submitted on : Tuesday, September 17, 2013 - 10:53:25 AM
Last modification on : Tuesday, July 13, 2021 - 2:17:01 PM
Long-term archiving on: : Wednesday, April 5, 2017 - 6:48:17 PM

File

lostanlen.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00849736, version 1

Citation

Vincent Lostanlen. Découverte automatique de structures musicales en temps réel par la géométrie de l'information. Son [cs.SD]. 2013. ⟨hal-00849736⟩

Share

Metrics

Record views

422

Files downloads

638