@article{multimodalandmultiscalespatial,
  title = {Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech},
  author = {Rui Liu and Shuwei He and Yifan Hu and Haizhou Li},
  year = {2024},
  eprint = {2412.11409},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.11409v3},
}