@inproceedings{zhang-etal-2022-speechut,
    title = "{S}peech{UT}: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training",
    author = "Zhang, Ziqiang  and
      Zhou, Long  and
      Ao, Junyi  and
      Liu, Shujie  and
      Dai, Lirong  and
      Li, Jinyu  and
      Wei, Furu",
    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/jlcl-multiple-ingestion/2022.emnlp-main.108/",
    doi = "10.18653/v1/2022.emnlp-main.108",
    pages = "1663--1676"
}