@article{learningcontextuallyfusedaudiovisual,
  title = {Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition},
  author = {Zi-Qiang Zhang and Jie Zhang and Jian-Shu Zhang and Ming-Hui Wu and Xin Fang and Li-Rong Dai},
  year = {2022},
  eprint = {2202.07428},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2202.07428v2},
}