@article{transferlearningfromaudiovisualgrounding,
  title = {Transfer Learning from Audio-Visual Grounding to Speech Recognition},
  author = {Wei-Ning Hsu and David Harwath and James Glass},
  year = {2019},
  eprint = {1907.04355},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1907.04355v1},
}