@article{syncvsrdataefficientvisualspeech,
  title = {SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization},
  author = {Young Jin Ahn and Jungwoo Park and Sangha Park and Jonghyun Choi and Kee-Eung Kim},
  year = {2024},
  eprint = {2406.12233},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.12233v1},
}