@inproceedings{liu-etal-2023-vit,
    title = "{V}i{T}-{TTS}: Visual Text-to-Speech with Scalable Diffusion Transformer",
    author = "Liu, Huadai  and
      Huang, Rongjie  and
      Lin, Xuan  and
      Xu, Wenqiang  and
      Zheng, Maozong  and
      Chen, Hong  and
      He, Jinzheng  and
      Zhao, Zhou",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.990/",
    doi = "10.18653/v1/2023.emnlp-main.990",
    pages = "15957--15969"
}