Login / Signup
RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations.
Neha Sahipjohn
Neil Kumar Shah
Vishal Tambrahalli
Vineet Gandhi
Published in:
CoRR (2023)
Keyphrases
</>
speech synthesis
speech recognition
prosodic features
vocal tract
higher level
text to speech
domain specific
real time
information retrieval
speaker verification
database
feature extraction
bayesian networks
pattern recognition
audio visual