@article{seeingspeechandsounddistinguishingand, title = {Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes}, author = {Hyeonggon Ryu and Seongyu Kim and Joon Son Chung and Arda Senocak}, year = {2025}, eprint = {2503.18880}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.18880v1}, }