Controllable End-to-End Neural Source–Filter Vocoder With Low-Dimensional Speech Parameters and Data Augmentation

Recent neural vocoders synthesize speech waveforms from high-dimensional spectrograms, making it difficult to control individual speech parameters such as F0 and formants. Neural formant synthesis (NF) has been proposed to control speech parameters by converting low-dimensional parameters into spect...

Descrición completa

Detalles Bibliográficos

Principais autores:	Sumiharu Kobayashi, Tetsuo Kosaka, Takashi Nose
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2026-01-01
Series:	IEEE Access
Assuntos:	Speech synthesis formant synthesis neural vocoder generative adversarial networks
Acceso en liña:	https://ieeexplore.ieee.org/document/11455988/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!