@inproceedings{visualvoiceaudiovisualspeechseparation,
  title = {VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency},
  author = {Ruohan Gao and Kristen Grauman},
  year = {2021},
  booktitle = {CVPR 2021 1},
  eprint = {2101.03149},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2101.03149v2},
}