@inproceedings{ye-etal-2023-clapspeech,
    title = "{CLAPS}peech: Learning Prosody from Text Context with Contrastive Language-Audio Pre-Training",
    author = "Ye, Zhenhui  and
      Huang, Rongjie  and
      Ren, Yi  and
      Jiang, Ziyue  and
      Liu, Jinglin  and
      He, Jinzheng  and
      Yin, Xiang  and
      Zhao, Zhou",
    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.518/",
    doi = "10.18653/v1/2023.acl-long.518",
    pages = "9317--9331"
}