SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization
Young Jin Ahn, Jung‐Woo Park, Sangha Park, Jonghyun Choi, Kee-Eung Kim
Topics & Concepts
Computer scienceSynchronization (alternating current)CrossmodalSpeech recognitionEnd-to-end principleAudio visualSecurity tokenPerceptionArtificial intelligenceMultimediaVisual perceptionComputer networkPsychologyNeuroscienceChannel (broadcasting)Speech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and Synthesis