Zero-Shot Personalized Lip-To-Speech Synthesis with Face Image Based Voice Control.

Zhengyan Sheng Yang Ai Zhen-Hua Ling

Published in: ICASSP (2023)

Keyphrases

speech synthesis
text to speech
speech recognition
prosodic features
vocal tract
human faces
control system
facial features
control method
e learning
control strategy
facial images
image acquisition
machine learning
language model
face images
computer vision