@misc{arxiv_2610_01012v1,
  title = {Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning},
  author = {{Gunwoo Lee} and {Yoori Oh} and {Yoseob Han}},
  eprint = {2610.01012v1},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.01012v1}
}