@inproceedings{wang-etal-2026-m3,
    title = "{M}3-{TTS}: Native Two-Stream Multi-Modal Diffusion Transformer for Zero-Shot Speech Synthesis",
    author = "Wang, Xiaopeng  and
      Qiang, Chunyu  and
      Fu, Ruibo  and
      Wen, Zhengqi  and
      Guo, Yuxin  and
      Liu, Xuefei  and
      Liu, Yukun  and
      Liang, Yuzhe  and
      Yin, Kang  and
      Ma, Teng  and
      Chen, Yushen  and
      Xie, Yuankun  and
      Li, Chenxing  and
      Li, Changsheng",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.findings-emnlp.240/",
    pages = "5061--5071",
    ISBN = "979-8-89176-462-0"
}