@inproceedings{zheng-etal-2025-voicecraft,
    title = "{V}oice{C}raft-{X}: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing",
    author = "Zheng, Zhisheng  and
      Peng, Puyuan  and
      Diwan, Anuj  and
      Huynh, Cong Phuoc  and
      Sun, Xiaohang  and
      Liu, Zhu  and
      Bhat, Vimal  and
      Harwath, David",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.137/",
    pages = "2737--2756",
    ISBN = "979-8-89176-332-6"
}