@inproceedings{wan-etal-2026-speech,
    title = "Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception",
    author = "Wan, Zhen  and
      Yang, Chao-Han Huck  and
      Tian, Jinchuan  and
      Ye, Hanrong  and
      Pasad, Ankita  and
      Fu, Szu-Wei  and
      Goel, Arushi  and
      Hachiuma, Ryo  and
      Diao, Shizhe  and
      Dhawan, Kunal  and
      Ghosh, Sreyan  and
      Hirota, Yusuke  and
      Chen, Zhehuai  and
      Valle, Rafael  and
      Chu, Chenhui  and
      Watanabe, Shinji  and
      Ginsburg, Boris  and
      Wang, Yu-Chiang Frank",
    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.1997/",
    pages = "43124--43142",
    ISBN = "979-8-89176-390-6"
}