@inproceedings{liang-etal-2024-aligncap,
    title = "{A}lign{C}ap: Aligning Speech Emotion Captioning to Human Preferences",
    author = "Liang, Ziqi  and
      Shi, Haoxiang  and
      Chen, Hanhui",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.emnlp-main.224/",
    doi = "10.18653/v1/2024.emnlp-main.224",
    pages = "3837--3846"
}