@article{crossmodalglobalinteractionandlocal, title = {Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition}, author = {Yuchen Hu and Ruizhe Li and Chen Chen and Heqing Zou and Qiushi Zhu and Eng Siong Chng}, year = {2023}, eprint = {2305.09212}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2305.09212v1}, }