@article{specmaskfoleysteeringpretrainedspectral, title = {SpecMaskFoley: Steering Pretrained Spectral Masked Generative Transformer Toward Synchronized Video-to-audio Synthesis via ControlNet}, author = {Zhi Zhong and Akira Takahashi and Shuyang Cui and Keisuke Toyama and Shusuke Takahashi and Yuki Mitsufuji}, year = {2025}, eprint = {2505.16195}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.16195v1}, }