Jiachen Lian, Alexei Baevski, Wei-Ning Hsu, Michael Auli. Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations. In IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Taipei, Taiwan, December 16-20, 2023. pages 1-8, IEEE, 2023. [doi]
@inproceedings{LianBHA23,
title = {Av-Data2Vec: Self-Supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations},
author = {Jiachen Lian and Alexei Baevski and Wei-Ning Hsu and Michael Auli},
year = {2023},
doi = {10.1109/ASRU57964.2023.10389642},
url = {https://doi.org/10.1109/ASRU57964.2023.10389642},
researchr = {https://researchr.org/publication/LianBHA23},
cites = {0},
citedby = {0},
pages = {1-8},
booktitle = {IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023, Taipei, Taiwan, December 16-20, 2023},
publisher = {IEEE},
isbn = {979-8-3503-0689-7},
}