Login / Signup
LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading.
Leyuan Qu
Cornelius Weber
Stefan Wermter
Published in:
IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
</>
lip reading
visual speech recognition
speaker identification
head tracking
visual speech
expression recognition
speech recognition
speech signal
noisy environments
real time
training set
hidden markov models
test set
image sequences
feature extraction
high resolution