@inproceedings{ijcai2023p564,
  title     = {Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition},
  author    = {Hu, Yuchen and Li, Ruizhe and Chen, Chen and Zou, Heqing and Zhu, Qiushi and Chng, Eng Siong},
  booktitle = {Proceedings of the Thirty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-23}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Edith Elkind},
  pages     = {5076--5084},
  year      = {2023},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2023/564},
  url       = {https://doi.org/10.24963/ijcai.2023/564},
}