Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning.

@inproceedings{xie-2025-audiodriven, author = {Yifan Xie and Fei Ma and Yi Bin and Ying He and Fei Yu}, editor = {Zhongfei Zhang and Elisa Ricci and Yan Yan and Liqiang Nie and Vincent Oria and Lamberto Ballan}, title = {{Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning}}, booktitle = {{Proceedings of the 2025 International Conference on Multimedia Retrieval, ICMR 2025, Chicago, IL, USA, 30 June 2025 - 3 July 2025}}, pages = {1588--1597}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3731715.3733279}, doi = {https://doi.org/10.1145/3731715.3733279} }