@article{seeingsoundslearningaudiotovisualalignme,
  title = {SeeingSounds: Learning Audio-to-Visual Alignment via Text},
  author = {Simone Carnemolla and Matteo Pennisi and Chiara Russo and Simone Palazzo and Daniela Giordano and Concetto Spampinato},
  year = {2025},
  eprint = {2510.11738},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.11738},
}