@article{unisonharmonizingmotionspeechandsoundfor, title = {Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation}, author = {Shihao Cheng and Jiaxu Zhang and Quanyue Song and Shansong Liu and Zhizhi Guo and Xiaolei Zhang and Chi Zhang and Xuelong Li and Zhigang Tu}, year = {2026}, eprint = {2605.08729}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2605.08729}, }