CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights - Institut de Recherche et Coordination Acoustique/Musique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights

Résumé

This paper tackles GAN optimization and stability issues in the context of voice conversion. First, to simplify the conversion task, we propose to use spectral envelopes as inputs. Second we propose two adversarial weight training paradigms, the generalized weighted GAN and the generator impact GAN, both aim at reducing the impact of the generator on the discriminator, so both can learn more gradually and efficiently during training. Applying an energy constraint to the cycleGAN paradigm considerably improved conversion quality. A subjective experiment conducted on a voice conversion task on the voice conversion challenge 2018 dataset shows first that despite a significantly reduced network complexity, the proposed method achieves state-of-the-art results, and second that the proposed weighted GAN methods outperform a previously proposed one.
Fichier principal
Vignette du fichier
1910.12614.pdf (1.1 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02929245 , version 1 (03-09-2020)

Identifiants

  • HAL Id : hal-02929245 , version 1

Citer

Rafael Ferro, Nicolas Obin, Axel Roebel. CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights. Eusipco, Aug 2020, Amsterdam, Netherlands. ⟨hal-02929245⟩
85 Consultations
121 Téléchargements

Partager

Gmail Facebook X LinkedIn More