Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels

Nicolas Obin
Axel Roebel
  • Fonction : Auteur
  • PersonId : 1100029

Résumé

This paper presents a end-to-end framework for the F0 transformation in the context of expressive voice conversion. A single neural network is proposed, in which a first module is used to learn F0 representation over different temporal scales and a second adversarial module is used to learn the transformation from one emotion to another. The first module is composed of a convolution layer with wavelet kernels so that the various temporal scales of F0 variations can be efficiently encoded. The single decomposition/transformation network allows to learn in a end-to-end manner the F0 decomposition that are optimal with respect to the transformation, directly from the raw F0 signal.
Fichier principal
Vignette du fichier
Towards_end-to-end_F0_voice_conversion_based_on_Dual-GAN_with_convolutional_wavelet_kernels_final_version.pdf (1.69 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03239583 , version 1 (27-05-2021)

Identifiants

  • HAL Id : hal-03239583 , version 1

Citer

Clément Le Moine, Nicolas Obin, Axel Roebel. Towards end-to-end F0 voice conversion based on Dual-GAN with convolutional wavelet kernels. EUSIPCO, 2021, Dublin (virtual ), Ireland. ⟨hal-03239583⟩
58 Consultations
99 Téléchargements

Partager

Gmail Facebook X LinkedIn More