@inproceedings{yang-etal-2024-audiovsr,
    title = "{A}udio{VSR}: Enhancing Video Speech Recognition with Audio Data",
    author = "Yang, Xiaoda  and
      Cheng, Xize  and
      Duan, Jiaqi  and
      Qiu, Hongshun  and
      Hong, Minjie  and
      Fang, Minghui  and
      Ji, Shengpeng  and
      Zuo, Jialong  and
      Hong, Zhiqing  and
      Zhang, Zhimeng  and
      Jin, Tao",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.858/",
    doi = "10.18653/v1/2024.emnlp-main.858",
    pages = "15352--15361"
}