most citedSyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AI2024★ 1 cited

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

Young Jin Ahn, Jungwoo Park, Sangha Park +2

Visual Speech Recognition (VSR) stands at the intersection of computer vision and speech recognition, aiming to interpret spoken content from visual cues. A prominent challenge in…