@article{vilasintegratingvisionandlanguageinto,
  title = {VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition},
  author = {Ziyi Ni and Minglun Han and Feilong Chen and Linghui Meng and Jing Shi and Pin Lv and Bo Xu},
  year = {2023},
  eprint = {2305.19972},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.19972v2},
}