@inproceedings{wang-etal-2025-vocalnet,
    title = "{V}ocal{N}et: Speech {LLM}s with Multi-Token Prediction for Faster and High-Quality Generation",
    author = "Wang, Yuhao  and
      Liu, Heyang  and
      Cheng, Ziyang  and
      Wu, Ronghua  and
      Gu, Qunshan  and
      Wang, Yanfeng  and
      Wang, Yu",
    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.989/",
    pages = "19595--19612",
    ISBN = "979-8-89176-332-6"
}