@article{selfsupervisedaudiovisualspeech,
  title = {Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation},
  author = {Jing-Xuan Zhang and Genshun Wan and Zhen-Hua Ling and Jia Pan and Jianqing Gao and Cong Liu},
  year = {2022},
  eprint = {2212.02782},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.02782v1},
}