UNET-TTS: Improving Unseen Speaker and Style Transfer in One-Shot Voice Cloning.

Rui Li Dong Pu Minnie Huang Bill Huang

Published in: ICASSP (2022)

Keyphrases

text to speech
prosodic features
speech synthesis
speaker verification
training set
speech recognition
audio visual
speaker recognition
synthesized speech
search engine
multimedia
feature extraction
automatic speech recognition
previously unseen
word processing