@inproceedings{jain-etal-2024-multi,
    title = "Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition",
    author = "Jain, Yash  and
      Chan, David M.  and
      Dheram, Pranav  and
      Khare, Aparna  and
      Shonibare, Olabanji  and
      Ravichandran, Venkatesh  and
      Ghosh, Shalini",
    editor = "Calzolari, Nicoletta  and
      Kan, Min-Yen  and
      Hoste, Veronique  and
      Lenci, Alessandro  and
      Sakti, Sakriani  and
      Xue, Nianwen",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    publisher = "ELRA and ICCL",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.lrec-main.1045/",
    pages = "11969--11980"
}