A Multidomain Generative Adversarial Network for Hoarse-to-Normal Voice Conversion.

Chu, Minghang; Wang, Jing; Fan, Zhiwei; Yang, Mengtao; Xu, Chao; Ma, Yaoyao; Tao, Zhi; Wu, Di

Chu, Minghang; Wang, Jing; Fan, Zhiwei; Yang, Mengtao; Xu, Chao; Ma, Yaoyao; Tao, Zhi; Wu, Di.

Afiliación

Chu M; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Wang J; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Fan Z; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Yang M; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Xu C; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Ma Y; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Tao Z; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China.
Wu D; School of Optoelectronic Science and Engineering, Soochow University, Suzhou, Jiangsu, China. Electronic address: wudi@suda.edu.cn.

J Voice ; 2023 Oct 14.

Article en En | MEDLINE | ID: mdl-37845148

Palabras clave

Artificial intelligence; Health sciences; Hoarse voice conversion; Intelligibility; Multidomain generative adversarial network; Pathological voice

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google

Texto completo: 1 Base de datos: MEDLINE Idioma: En Revista: J Voice Asunto de la revista: OTORRINOLARINGOLOGIA Año: 2023 Tipo del documento: Article País de afiliación: China

Texto completo

Imprimir

XML

PubMed Links

Buscar en Google