@inproceedings{pan-etal-2022-leveraging,
    title = "Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition",
    author = "Pan, Xichen  and
      Chen, Peiyu  and
      Gong, Yichen  and
      Zhou, Helong  and
      Wang, Xinbing  and
      Lin, Zhouhan",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.acl-long.308/",
    doi = "10.18653/v1/2022.acl-long.308",
    pages = "4491--4503"
}