@inproceedings{fromfacestovoiceslearninghierarchical,
  title = {From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech},
  author = {Ji-Hoon Kim and Jeongsoo Choi and Jaehun Kim and Chaeyoung Jung and Joon Son Chung},
  year = {2025},
  booktitle = {CVPR 2025 1},
  eprint = {2503.16956},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.16956v1},
}