@article{selfsupervisedrepresentationlearningfor8,
  title = {Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling},
  author = {Puyuan Peng and David Harwath},
  year = {2022},
  eprint = {2202.03543},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2202.03543v2},
}