@inproceedings{shen-etal-2026-vocalrep,
    title = "{V}ocal{R}ep: Structure-Aware Vocal Representations for Multimodal Generation",
    author = "Shen, Da  and
      Weng, Zhenqiang  and
      Liu, Tianyu  and
      Chen, Gongyu  and
      Shi, Runhua  and
      Chen, Jiahui  and
      Ding, Chaofan  and
      Zhang, Wei-Qiang  and
      Chen, Zihao",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1785/",
    pages = "35850--35865",
    ISBN = "979-8-89176-395-1"
}