@inproceedings{getman-etal-2025-towards,
    title = "Towards large-scale speech foundation models for a low-resource minority language",
    author = "Getman, Yaroslav  and
      Gr{\'o}sz, Tam{\'a}s  and
      Hiovain-Asikainen, Katri  and
      Lehtonen, Tommi  and
      Kurimo, Mikko",
    editor = "Johansson, Richard  and
      Stymne, Sara",
    booktitle = "Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)",
    month = mar,
    year = "2025",
    address = "Tallinn, Estonia",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.nodalida-1.19/",
    pages = "192--200",
    ISBN = "978-9908-53-109-0",
    abstract = "Modern ASR systems require massive amounts of training data. While ASR training data for most languages are scarce and expensive to transcribe, a practical solution is to collect huge amounts of raw untranscribed speech and pre-train the ASR model in a self-supervised manner. Unfortunately, for many low-resource minority languages, even untranscribed speech data are scarce. In this paper, we propose a solution for the Northern S{\'a}mi language with 22,400 hours of speech extracted from the Finnish radio and television archives. We evaluated the model performance with different decoding algorithms and examined the models' internal behavior with interpretation-based techniques."
}