@inproceedings{cai-etal-2023-masked,
    title = "Masked Audio Text Encoders are Effective Multi-Modal Rescorers",
    author = "Cai, Jinglun  and
      Sunkara, Monica  and
      Li, Xilai  and
      Bhatia, Anshu  and
      Pan, Xiao  and
      Bodapati, Sravan",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2023.findings-acl.682/",
    doi = "10.18653/v1/2023.findings-acl.682",
    pages = "10718--10730"
}