@inproceedings{cheng-etal-2025-integrating,
    title = "Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party Conversation",
    author = "Cheng, Luyao  and
      Wang, Hui  and
      Deng, Chong  and
      Zheng, Siqi  and
      Chen, Yafeng  and
      Huang, Rongjie  and
      Zhang, Qinglin  and
      Chen, Qian  and
      Li, Xihao  and
      Wang, Wen",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.977/",
    pages = "19914--19928",
    ISBN = "979-8-89176-251-0"
}