Reconstruction of Speech Signals from their Unpredictable Points Manifold

Abstract : This paper shows that a microcanonical approach to complexity, such as the Microcanonical Multiscale Formalism, provides new insights to analyze non-linear dynamics of speech, specifically in relation to the problem of speech samples classification according to their information content. Central to the approach is the precise computation of Local Predictability Exponents (LPEs) according to a procedure based on the evaluation of the degree of reconstructibility around a given point. We show that LPEs are key quantities related to predictability in the framework of reconstructible systems: it is possible to reconstruct the whole speech signal by applying a reconstruction kernel to a small subset of points selected according to their LPE value. This provides a strong indication of the importance of the Unpredictable Points Manifold(UPM), already demonstrated for other types of complex signals. Experiments show that a UPM containing around 12% of the points providesvery good perceptual reconstruction quality.
Type de document :
Communication dans un congrès
NOn LInear Speech Processing 2011, Nov 2011, Las Palmas de Gran Canaria, Spain. Springer, 7015, 2011, Lecture Notes in Computer Science
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00647197
Contributeur : Vahid Khanagha <>
Soumis le : jeudi 1 décembre 2011 - 16:15:40
Dernière modification le : jeudi 11 janvier 2018 - 06:21:34
Document(s) archivé(s) le : vendredi 16 novembre 2012 - 12:40:50

Fichier

KHANAGHA_Reconstruction_of_spe...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00647197, version 1

Collections

Citation

Vahid Khanagha, Hussein Yahia, Khalid Daoudi, Oriol Pont, Antonio Turiel. Reconstruction of Speech Signals from their Unpredictable Points Manifold. NOn LInear Speech Processing 2011, Nov 2011, Las Palmas de Gran Canaria, Spain. Springer, 7015, 2011, Lecture Notes in Computer Science. 〈hal-00647197〉

Partager

Métriques

Consultations de la notice

472

Téléchargements de fichiers

244