Automatic Voice Identification after Speech Resynthesis using PPG - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Automatic Voice Identification after Speech Resynthesis using PPG

Résumé

Speech resynthesis is a generic task for which we want to synthesize audio with another audio as input, which finds applications for media monitors and journalists. Among different tasks addressed by speech resynthesis, voice conversion preserves the linguistic information while modifying the identity of the speaker, and speech edition preserves the identity of the speaker but some words are modified. In both cases, we need to disentangle speaker and phonetic contents in intermediate representations. Phonetic PosteriorGrams (PPG) are a frame-level probabilistic representation of phonemes, and are usually considered speaker-independent. This paper presents a PPG-based speech resynthesis system. A perceptive evaluation assesses that it produces correct audio quality. Then, we demonstrate that an automatic speaker verification model is not able to recover the source speaker after re-synthesis with PPG, even when the model is trained on synthetic data.
Fichier principal
Vignette du fichier
Odyssey_PPG_Conversion.pdf (285.87 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04638686 , version 1 (05-08-2024)

Identifiants

Citer

Thibault Gaudier, Marie Tahon, Anthony Larcher, Yannick Estève. Automatic Voice Identification after Speech Resynthesis using PPG. Speaker and Language Recognition Workshop - Odyssey, Jun 2024, Québec (Canada), Canada. ⟨hal-04638686⟩
50 Consultations
25 Téléchargements

Altmetric

Partager

More