@inproceedings{zhang-etal-2025-leveraging-unit,
    title = "Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation",
    author = "Zhang, Yuhao  and
      Ma, Xiangnan  and
      Kou, Kaiqi  and
      Liu, Peizhuo  and
      Shan, Weiqiao  and
      Wang, Benyou  and
      Xiao, Tong  and
      Huang, Yuxin  and
      Yu, Zhengtao  and
      Zhu, JingBo",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.75/",
    pages = "1448--1460",
    ISBN = "979-8-89176-256-5",
    abstract = "The success of building textless speech-to-speech translation (S2ST) models has attracted much attention. However, S2ST still faces two main challenges: 1) extracting linguistic features for various speech signals, called cross-modal (CM), and 2) learning alignment of difference languages in long sequences, called cross-lingual (CL). We propose the unit language to overcome the two modeling challenges. The unit language can be considered a text-like representation format, constructed using $n$-gram language modeling. We implement multi-task learning to utilize the unit language in guiding the speech modeling process. Our initial results reveal a conflict when applying source and target unit languages simultaneously. We propose task prompt modeling to mitigate this conflict. We conduct experiments on four languages of the Voxpupil dataset. Our method demonstrates significant improvements over a strong baseline and achieves performance comparable to models trained with text."
}