Application of the microcanonical Multiscale formalism to segmentation of speech signals

Vahid Khanagha 1 Khalid Daoudi 1, 2 Oriol Pont 1 Hussein Yahia 1
1 GeoStat - Geometry and Statistics in acquisition data
Inria Bordeaux - Sud-Ouest
2 IRIT - Institut de recherche en informatique de Toulouse
Abstract : In this paper we use a novel framework, the Microcanonical Multiscale Formalism (MMF), to analyze speech signals. The MMF is based on the computation of geometrical and local parameters -the singularity exponents- which allow nonlinear analysis of their complex dynamics and, particularly, characterize their intermittent signature. We define an accumulative measure on these exponents which has the nice property of producing clear and distinctive changes at phoneme boundaries. We present preliminary experiments on the TIMIT database, which show that singular exponents convey indeed valuable information about the local dynamics of speech. They also show that the measure we define has a good potential to provide a new and powerful method for text-independent phonetic segmentation.
Keywords : nonlinear speech analysis phonetic segmentation
Type de document :
Communication dans un congrès
2010 European Signal Processing Conference (EUSIPCO-2010), Aug 2010, Aalborg, Denmark. pp.100-104, 2010
Liste complète des métadonnées
https://hal.inria.fr/inria-00533101
Contributeur : Vahid Khanagha <>
Soumis le : vendredi 5 novembre 2010 - 11:05:20
Dernière modification le : mercredi 14 novembre 2018 - 13:54:11

Identifiants

  • HAL Id : inria-00533101, version 1

Collections

INRIA | UNIV-TLSE3 | UNIV-TLSE2 | INRIA-BORDEAUX | SMS

Citation

Vahid Khanagha, Khalid Daoudi, Oriol Pont, Hussein Yahia. Application of the microcanonical Multiscale formalism to segmentation of speech signals. 2010 European Signal Processing Conference (EUSIPCO-2010), Aug 2010, Aalborg, Denmark. pp.100-104, 2010. 〈inria-00533101〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

320

Contact


archive-ouverte@inria.fr