@article{deepvisualforcedalignmentlearningto,
  title = {Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video},
  author = {Minsu Kim and Chae Won Kim and Yong Man Ro},
  year = {2023},
  eprint = {2303.08670},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2303.08670v1},
}