@article{audiovisualspeechseparationbasedonjoint,
  title = {Audio-visual speech separation based on joint feature representation with cross-modal attention},
  author = {Junwen Xiong and Peng Zhang and Lei Xie and Wei Huang and Yufei zha and Yanning Zhang},
  year = {2022},
  eprint = {2203.02655},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2203.02655v1},
}