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...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Sumiharu Kobayashi, Tetsuo Kosaka, Takashi Nose
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	IEEE 2026-01-01
Serie:	IEEE Access
Soggetti:	Speech synthesis formant synthesis neural vocoder generative adversarial networks
Accesso online:	https://ieeexplore.ieee.org/document/11455988/
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!