@inproceedings{zhao-etal-2022-connecting,
    title = "Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge Transfer",
    author = "Zhao, Yanpeng  and
      Hessel, Jack  and
      Yu, Youngjae  and
      Lu, Ximing  and
      Zellers, Rowan  and
      Choi, Yejin",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "http://aclanthology.org/2022.naacl-main.333/",
    doi = "10.18653/v1/2022.naacl-main.333",
    pages = "4492--4507"
}