@inproceedings{lin-etal-2023-tavt,
    title = "{TAVT}: Towards Transferable Audio-Visual Text Generation",
    author = "Lin, Wang  and
      Jin, Tao  and
      Pan, Wenwen  and
      Li, Linjun  and
      Cheng, Xize  and
      Wang, Ye  and
      Zhao, Zhou",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.836/",
    doi = "10.18653/v1/2023.acl-long.836",
    pages = "14983--14999"
}