@article{vatlmvisualaudiotextpretrainingwith,
  title = {VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning},
  author = {Qiushi Zhu and Long Zhou and Ziqiang Zhang and Shujie Liu and Binxing Jiao and Jie Zhang and LiRong Dai and Daxin Jiang and Jinyu Li and Furu Wei},
  year = {2022},
  eprint = {2211.11275},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.11275v2},
}