Improving text-independent phonetic segmentation based on the Microcanonical Multiscale Formalism

Abstract : In an earlier work, we proposed a novel phonetic segmentation method based on speech analysis under the Microcanonical Multiscale Formalism (MMF). The latter relies on the computation of local geometrical parameters, singularity exponents (SE). We showed that SE convey valuable information about the local dynamics of speech that can readily and simply used to detect phoneme boundaries. By performing error analysis of our original algorithm, in this paper we propose a 2-steps technique which better exploits SE to improve the segmentation accuracy. In the first step, we detect the boundaries of the original signal and of a low-pass filtred version, and we consider the union of all detected boundaries as candidates. In the second step, we use a hypothesis test over the local SE distribution of the original signal to select the final boundaries. We carry out a detailed evaluation and comparison over the full training set of the TIMIT database which could be useful to other researchers for comparison purposes. The results show that the new algorithm not only outperforms the original one, but also is significantly much more accurate than state-of-the-art ones.
Type de document :
Communication dans un congrès
ICASSP 2011, May 2011, Prague, Czech Republic. 2011
Liste complète des métadonnées

https://hal.inria.fr/inria-00557661
Contributeur : Vahid Khanagha <>
Soumis le : lundi 23 avril 2012 - 11:14:47
Dernière modification le : mercredi 3 janvier 2018 - 14:18:08
Document(s) archivé(s) le : lundi 26 novembre 2012 - 15:25:39

Fichier

myICASSP2.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00557661, version 1

Collections

Citation

Vahid Khanagha, Daoudi Khalid, Oriol Pont, Hussein Yahia. Improving text-independent phonetic segmentation based on the Microcanonical Multiscale Formalism. ICASSP 2011, May 2011, Prague, Czech Republic. 2011. 〈inria-00557661〉

Partager

Métriques

Consultations de la notice

314

Téléchargements de fichiers

240