@article{vitttsvisualtexttospeechwithscalable,
  title = {ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer},
  author = {Huadai Liu and Rongjie Huang and Xuan Lin and Wenqiang Xu and Maozong Zheng and Hong Chen and Jinzheng He and Zhou Zhao},
  year = {2023},
  eprint = {2305.12708},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.12708v2},
}