Code for "Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection"is available at: https://github.com/rash1993/movie-asd
Please cite the following works if you use this framework.
@ARTICLE{10102534,
author={Sharma, Rahul and Narayanan, Shrikanth},
journal={IEEE Open Journal of Signal Processing},
title={Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection},
year={2023},
volume={4},
number={},
pages={225-232},
doi={10.1109/OJSP.2023.3267269}}
@article{sharma2022unsupervised,
title={Unsupervised active speaker detection in media content using cross-modal information},
author={Sharma, Rahul and Narayanan, Shrikanth},
journal={arXiv preprint arXiv:2209.11896},
year={2022}
}