Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, Zhouhan Lin. Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition. In Smaranda Muresan, Preslav Nakov, Aline Villavicencio, editors, Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022. pages 4491-4503, Association for Computational Linguistics, 2022. [doi]
@inproceedings{PanCGZWL22,
title = {Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition},
author = {Xichen Pan and Peiyu Chen and Yichen Gong and Helong Zhou and Xinbing Wang and Zhouhan Lin},
year = {2022},
url = {https://aclanthology.org/2022.acl-long.308},
researchr = {https://researchr.org/publication/PanCGZWL22},
cites = {0},
citedby = {0},
pages = {4491-4503},
booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022},
editor = {Smaranda Muresan and Preslav Nakov and Aline Villavicencio},
publisher = {Association for Computational Linguistics},
isbn = {978-1-955917-21-6},
}