A vision-integrated neural speech codec that uses lip images, via explicit fusion or distillation, improves decoded speech quality and noise robustness at 6 kbps.
Recommendation g.726: 40, 32, 24, and 16 kbps adap- tive differential pulse code modulation (ADPCM),
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Vision-Integrated High-Quality Neural Speech Coding
A vision-integrated neural speech codec that uses lip images, via explicit fusion or distillation, improves decoded speech quality and noise robustness at 6 kbps.