Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Haithem Boussaid, Ebtesam Almazrouei, Mérouane Debbah. Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping. In IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023. pages 13744-13755, IEEE, 2023. [doi]
@inproceedings{DjilaliNBAD23,
title = {Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping},
author = {Yasser Abdelaziz Dahou Djilali and Sanath Narayan and Haithem Boussaid and Ebtesam Almazrouei and Mérouane Debbah},
year = {2023},
doi = {10.1109/ICCV51070.2023.01268},
url = {https://doi.org/10.1109/ICCV51070.2023.01268},
researchr = {https://researchr.org/publication/DjilaliNBAD23},
cites = {0},
citedby = {0},
pages = {13744-13755},
booktitle = {IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, October 1-6, 2023},
publisher = {IEEE},
isbn = {979-8-3503-0718-4},
}