Prediction of Cepstral Excitation Pulses for Voice Conversion

Abstract : Voice conversion is one of useful techniques to enhance pathological speech to be perceived as normal speech, although it concerns also the modifications of normal source speaker's speech to be perceived as if a target speaker had uttered it. The parameters to be converted are obtained by matching the spectral envelope of the vocal tract for the source and the target speech. Gaussian Mixture Models (GMMs) parameters are determined for providing conversion functions. The main contribution of our study consists in the prediction of Fourier cepstrum coefficients related to the excitation signal. Such a prediction leads to a satisfactory voice conversion system. Subjective perceptual results indicate that the proposed approach yields significant improvements in quality of the converted voice.
Type de document :
Communication dans un congrès
5th. International Conference on Information Systems and Economic Intelligence - SIIE ̓ 2012, Feb 2012, Djerba, Tunisia. 2012
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00761776
Contributeur : Joseph Di Martino <>
Soumis le : lundi 10 décembre 2012 - 09:43:12
Dernière modification le : jeudi 11 janvier 2018 - 06:19:56
Document(s) archivé(s) le : lundi 11 mars 2013 - 11:21:25

Fichier

article_siie_2012_Bahja_Fadoua...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00761776, version 1

Collections

Citation

Fadoua Bahja, Joseph Di Martino, El Hassan Ibn Elhaj, Driss Aboutajdine. Prediction of Cepstral Excitation Pulses for Voice Conversion. 5th. International Conference on Information Systems and Economic Intelligence - SIIE ̓ 2012, Feb 2012, Djerba, Tunisia. 2012. 〈hal-00761776〉

Partager

Métriques

Consultations de la notice

613

Téléchargements de fichiers

234