Serveur © IRCAM - CENTRE POMPIDOU 1996-2005.
Tous droits réservés pour tous pays. All rights reserved.

Feature extraction and temporal segmentation of acoustic signals

S. Rossignol, X. Rodet, J. Soumagne, J.-L. Collette and P. Depalle

ICMC: International Computer Music Conference, Ann Arbor, USA, Octobre 1998.
Copyright © Ircam - Centre Georges-Pompidou 1998, 1999

La lecture des équations dans cet article requiert l'installation préliminaire de WebEq (applet Java).
This article needs the WebEq Java applet for equation display.

This paper deals with temporal segmentation of acoustic signals and feature extraction. Segmentation and feature extraction are aimed at being a first step for sound signal representation, coding, transformation, indexation and multimedia. Three interdependent schemes of segmentation are defined, which correspond to different levels of signal attributes. A complete segmentation and feature extraction system is shown. Applications and results on various examples are presented. The paper is divided into four sections : a definition of the segmentation schemes; and description of the techniques used for each of them.

La version électronique de ce texte n'est disponible dans son intégralité
qu'à partir des postes de consultation de l'Ircam, pour des raisons de copyright .

Les rapports de recherche et les revues musicales de l'Ircam (ainsi que des
disques, des brochures d'information...) peuvent être commandés auprès du
service de Communication de l'Ircam (tél: 01 44 78 48 98).

The full online version of this text is available only from within IRCAM,
for copyright reasons.

The Technical Reports, all the IRCAM periodicals as well as other publications (recordings, brochures, etc.) can be ordered from the IRCAM PR services
(phone: +33 (0) 1 44 78 48 98).