A method for simultaneously extract the fundamental frequency of a speech signal and segment it

Abstract : This paper deals with the voiced/unvoiced segmentation of natural speech signals and, inside the voiced intervals of these signals, with the determination of the fundamental frequency f0. Our primary motivation of developing the method presented in this paper is to obtain precise f0 information, this both in terms of frequency for relatively fast evolving events, and in terms of time location of these frequential events. The use of a first partial enhancement and of the Analytic Signal extraction techniques allows this. Comparisons with a standard FFT-based method are provided.
Type de document :
Communication dans un congrès
ISSPIT 2008, Dec 2008, Sarajevo, Bosnia and Herzegovina. pp.213-218, 2008
Liste complète des métadonnées

https://hal-supelec.archives-ouvertes.fr/hal-00351272
Contributeur : Sébastien Van Luchene <>
Soumis le : jeudi 8 janvier 2009 - 18:55:16
Dernière modification le : vendredi 9 janvier 2009 - 09:29:26

Identifiants

  • HAL Id : hal-00351272, version 1

Collections

Citation

Stéphane Rossignol, Jean-Luc Collette. A method for simultaneously extract the fundamental frequency of a speech signal and segment it. ISSPIT 2008, Dec 2008, Sarajevo, Bosnia and Herzegovina. pp.213-218, 2008. 〈hal-00351272〉

Partager

Métriques

Consultations de la notice

63