@inproceedings{ijcai2021p141, title = {Speech2Talking-Face: Inferring and Driving a Face with Synchronized Audio-Visual Representation}, author = {Sun, Yasheng and Zhou, Hang and Liu, Ziwei and Koike, Hideki}, booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, {IJCAI-21}}, publisher = {International Joint Conferences on Artificial Intelligence Organization}, editor = {Zhi-Hua Zhou}, pages = {1018--1024}, year = {2021}, month = {8}, note = {Main Track}, doi = {10.24963/ijcai.2021/141}, url = {https://doi.org/10.24963/ijcai.2021/141}, }