Jing-Xuan Zhang, Genshun Wan, Zhen-Hua Ling, Jia Pan, Jianqing Gao, Cong Liu 0006. Self-Supervised Audio-Visual Speech Representations Learning by Multimodal Self-Distillation. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]
@inproceedings{ZhangWLPGL23,
title = {Self-Supervised Audio-Visual Speech Representations Learning by Multimodal Self-Distillation},
author = {Jing-Xuan Zhang and Genshun Wan and Zhen-Hua Ling and Jia Pan and Jianqing Gao and Cong Liu 0006},
year = {2023},
doi = {10.1109/ICASSP49357.2023.10095029},
url = {https://doi.org/10.1109/ICASSP49357.2023.10095029},
researchr = {https://researchr.org/publication/ZhangWLPGL23},
cites = {0},
citedby = {0},
pages = {1-5},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023},
publisher = {IEEE},
isbn = {978-1-7281-6327-7},
}