On the use of spectral peak parameters in voice conversion - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

On the use of spectral peak parameters in voice conversion

Résumé

This paper addresses the problem of low transformed data variance, or "over-smoothing," in spectral transformation for Voice Conversion. In examining a classic GMM-based transformation with cepstral coefficients, we show that this problem lies, not only in the transformation model (as commonly assumed), but also in the choice of spectral parameterization. Consequently, we propose an alternative method for spectral transformation using spectral peaks and an HMM with Gaussian state distributions. The spectral peaks are shown to offer higher inter-speaker feature correlation and yield higher transformed data variance than their cepstral coefficient counterparts. Additionally, the accuracy of the transformed envelopes is examined.
Fichier principal
Vignette du fichier
Interspeech2010.pdf (50.62 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00725505 , version 1 (27-08-2012)

Identifiants

  • HAL Id : hal-00725505 , version 1

Citer

Elizabeth Godoy, Olivier Rosec, Thierry Chonavel. On the use of spectral peak parameters in voice conversion. Interspeech 2010, Sep 2010, Makuhari, Japan. ⟨hal-00725505⟩
68 Consultations
163 Téléchargements

Partager

Gmail Facebook X LinkedIn More