@inproceedings{pandey-etal-2025-sift,
    title = "{SIFT}-50{M}: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning",
    author = "Pandey, Prabhat  and
      Swaminathan, Rupak Vignesh  and
      Girish, K V Vijay  and
      Sen, Arunasish  and
      Xie, Jian.  and
      Strimel, Grant  and
      Schwarz, Andreas",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.acl-long.681/",
    pages = "13921--13942",
    ISBN = "979-8-89176-251-0"
}