Login / Signup

SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization.

Young Jin AhnJungwoo ParkSangha ParkJonghyun ChoiKee-Eung Kim
Published in: CoRR (2024)
Keyphrases
  • end to end
  • multimedia
  • feature extraction
  • multiscale
  • quality of service
  • congestion control