@inproceedings{qiang-etal-2026-unisonate,
    title = "{U}ni{S}onate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions",
    author = "Qiang, Chunyu  and
      Wang, Xiaopeng  and
      Yin, Kang  and
      Liang, Yuzhe  and
      Guo, Yuxin  and
      Ma, Teng  and
      Zhang, Ziyu  and
      Wang, Tianrui  and
      Gong, Cheng  and
      Chen, Yushen  and
      Fu, Ruibo  and
      Wang, Longbiao  and
      Dang, Jianwu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1293/",
    pages = "28043--28054",
    ISBN = "979-8-89176-390-6"
}