@inproceedings{han-etal-2024-xlavs,
    title = "{XLAVS}-{R}: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception",
    author = "Han, HyoJung  and
      Anwar, Mohamed  and
      Pino, Juan  and
      Hsu, Wei-Ning  and
      Carpuat, Marine  and
      Shi, Bowen  and
      Wang, Changhan",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.acl-long.697/",
    doi = "10.18653/v1/2024.acl-long.697",
    pages = "12896--12911"
}