@inproceedings{hsu-etal-2021-text,
    title = "Text-Free Image-to-Speech Synthesis Using Learned Segmental Units",
    author = "Hsu, Wei-Ning  and
      Harwath, David  and
      Miller, Tyler  and
      Song, Christopher  and
      Glass, James",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.acl-long.411/",
    doi = "10.18653/v1/2021.acl-long.411",
    pages = "5284--5300"
}