@article{leveragingaudiovisualdatatoreducethemult,
  title = {Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models},
  author = {María Andrea Cruz Blandón and Zakaria Aldeneh and Jie Chi and Maureen de Seyssel},
  year = {2025},
  eprint = {2509.17523},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2509.17523},
}