@inproceedings{wang-etal-2022-discrete,
    title = "Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation",
    author = "Wang, Chen  and
      Liu, Yuchen  and
      Chen, Boxing  and
      Zhang, Jiajun  and
      Luo, Wei  and
      Huang, Zhongqiang  and
      Zong, Chengqing",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.emnlp-main.354/",
    doi = "10.18653/v1/2022.emnlp-main.354",
    pages = "5291--5302"
}