@inproceedings{ijcai2024p0709,
  title     = {Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction},
  author    = {Mu, Zhaoxi and Yang, Xinyu},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-24}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Kate Larson},
  pages     = {6415--6423},
  year      = {2024},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2024/709},
  url       = {https://doi.org/10.24963/ijcai.2024/709},
}