@article{efficientaudiovisualspeechseparationwith,
  title = {Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention},
  author = {Kai Li and Kejun Gao and Xiaolin Hu},
  year = {2025},
  eprint = {2509.23610},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.23610},
}