@article{avdata2vecselfsupervisedlearningofaudio,
  title = {AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations},
  author = {Jiachen Lian and Alexei Baevski and Wei-Ning Hsu and Michael Auli},
  year = {2023},
  eprint = {2302.06419},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.06419v2},
}