@inproceedings{yu-etal-2023-speech,
    title = "Speech-Text Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment",
    author = "Yu, Tianshu  and
      Gao, Haoyu  and
      Lin, Ting-En  and
      Yang, Min  and
      Wu, Yuchuan  and
      Ma, Wentao  and
      Wang, Chao  and
      Huang, Fei  and
      Li, Yongbin",
    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.438/",
    doi = "10.18653/v1/2023.acl-long.438",
    pages = "7900--7913"
}