W2VC: WavLM representation based one-shot voice conversion with gradient reversal distillation and CTC supervision

Abstract Non-parallel data voice conversion (VC) has achieved considerable breakthroughs due to self-supervised pre-trained representation (SSPR) being used in recent years. Features extracted by the pre-trained model are expected to contain more content information. However, in common VC with SSPR,...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Hao Huang, Lin Wang, Jichen Yang, Ying Hu, Liang He
Formato:	Artigo
Idioma:	Inglês
Publicado em:	SpringerOpen 2023-10-01
coleção:	EURASIP Journal on Audio, Speech, and Music Processing
Assuntos:	Voice conversion Self-supervised pre-trained Representation Gradient reversal layer (GRL) CTC
Acesso em linha:	https://doi.org/10.1186/s13636-023-00312-8
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!