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...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Sumiharu Kobayashi, Tetsuo Kosaka, Takashi Nose
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2026-01-01
Saila:	IEEE Access
Gaiak:	Speech synthesis formant synthesis neural vocoder generative adversarial networks
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/11455988/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!