@inproceedings{liang-levow-2025-breaking,
    title = "Breaking the Transcription Bottleneck: Fine-tuning {ASR} Models for Extremely Low-Resource Fieldwork Languages",
    author = "Liang, Siyu  and
      Levow, Gina-Anne",
    editor = "Le Ferrand, {\'E}ric  and
      Klyachko, Elena  and
      Postnikova, Anna  and
      Shavrina, Tatiana  and
      Serikov, Oleg  and
      Voloshina, Ekaterina  and
      Vylomova, Ekaterina",
    booktitle = "Proceedings of the Fourth Workshop on NLP Applications to Field Linguistics",
    month = aug,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/transition-to-people-yaml/2025.fieldmatters-1.3/",
    pages = "26--37",
    ISBN = "979-8-89176-282-4",
    abstract = "The development of Automatic Speech Recognition (ASR) has yielded impressive results, but its use in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including spontaneous speech, environmental noise, and severely constrained datasets from under-documented languages. In this paper, we benchmark the performance of two fine-tuned multilingual ASR models, MMS and XLS-R, on five typologically diverse low-resource languages with control of training data duration. Our findings show that MMS is best suited when extremely small amounts of training data are available, whereas XLS-R shows parity performance once training data exceed one hour. We provide linguistically grounded analysis for further provide insights towards practical guidelines for field linguists, highlighting reproducible ASR adaptation approaches to mitigate the transcription bottleneck in language documentation."
}