@article{visualcontextdrivenaudiofeature,
  title = {Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition},
  author = {Joanna Hong and Minsu Kim and Daehun Yoo and Yong Man Ro},
  year = {2022},
  eprint = {2207.06020},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2207.06020v1},
}