@inproceedings{av2avdirectaudiovisualspeechtoaudio,
  title = {AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation},
  author = {Jeongsoo Choi and Se Jin Park and Minsu Kim and Yong Man Ro},
  year = {2023},
  booktitle = {CVPR 2024 1},
  eprint = {2312.02512},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.02512v2},
}