Non-Parallel Voice Conversion System Using An Auto-Regressive Model - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Non-Parallel Voice Conversion System Using An Auto-Regressive Model

Résumé

Much existing voice conversion (VC) systems are attractive owing to their high performance in terms of voice quality and speaker similarity. Nevertheless, without parallel training data, some generated waveform trajectories are not yet smooth, leading to degraded sound quality and mispronunciation issues in the converted speech. To address these shortcomings, this paper proposes a non-parallel VC system based on an auto-regressive model, Phonetic PosteriorGrams (PPGs), and an LPCnet vocoder to generate high-quality converted speech. The proposed auto-regressive structure makes our system able to produce the next step outputs from the previous step acoustic features. Further, the use of PPGs aims to convert any unknown source speaker into a specific target speaker due to their speaker-independent properties. We evaluate the effectiveness of our system by performing any-to-one conversion pairs between native English speakers. Objective and subjective measures show that our method outperforms the best non-parallel VC method of Voice Conversion Challenge 2018 in terms of naturalness and speaker similarity.
Fichier non déposé

Dates et versions

hal-03780125 , version 1 (19-09-2022)

Identifiants

Citer

Kadria Ezzine, Mondher Frikha, Joseph Di Martino. Non-Parallel Voice Conversion System Using An Auto-Regressive Model. 5th International Conference on Advanced Systems and Emergent Technologies - IC_ASET 2022, Mar 2022, Hammamet, Tunisia. pp.500-504, ⟨10.1109/IC_ASET53395.2022.9765886⟩. ⟨hal-03780125⟩
27 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More