@article{abridgefromaudiotovideophonemevisemealig, title = {A Bridge from Audio to Video: Phoneme-Viseme Alignment Allows Every Face to Speak Multiple Languages}, author = {Zibo Su and Kun Wei and Jiahua Li and Xu Yang and Cheng Deng}, year = {2025}, eprint = {2510.06612}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.06612}, }