Neural Vocoding for Singing and Speaking Voices with the Multi-Band Excited WaveNet

The use of the mel spectrogram as a signal parameterization for voice generation is quite recent and linked to the development of neural vocoders. These are deep neural networks that allow reconstructing high-quality speech from a given mel spectrogram. While initially developed for speech synthesis...

Descrición completa

Detalles Bibliográficos

Principais autores:	Axel Roebel, Frederik Bous
Formato:	Artigo
Idioma:	Inglês
Publicado:	MDPI AG 2022-02-01
Series:	Information
Assuntos:	neural vocoder mel spectrogram speech synthesis singing synthesis singing transformation speech transformation
Acceso en liña:	https://www.mdpi.com/2078-2489/13/3/103
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!