An AV2vec lipreading system transferred from English to Chinese, adapted to target speakers, and ensembled across face and lip inputs achieves 77.3% CER on ChatCLR.
, author Fainberg, J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Target Speaker Lipreading by Audio-Visual Self-Distillation Pretraining and Speaker Adaptation
An AV2vec lipreading system transferred from English to Chinese, adapted to target speakers, and ensembled across face and lip inputs achieves 77.3% CER on ChatCLR.