@inproceedings{kriukova-etal-2026-data,
    title = {A data-centric approach to performance improvement in under-resourced {ASR}: The case of D{\"e}n{\"e} S{\k{u}}{\l}{\i}n{\'e}},
    author = "Kriukova, Olga  and
      Lovick, Olga  and
      Arppe, Antti",
    editor = "Mager, Manuel  and
      Ebrahimi, Abteen  and
      Bui, Minh Duc  and
      Pugh, Robert  and
      Oncevay, Arturo  and
      Chiruzzo, Luis  and
      Solano, Rolando Coto  and
      Rijhwani, Shruti  and
      Von Der Wense, Katharina",
    booktitle = "Proceedings of the Sixth Workshop on {NLP} for Indigenous Languages of the {A}mericas ({A}mericas{NLP})",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.americasnlp-6.9/",
    pages = "95--106",
    ISBN = "979-8-89176-415-6",
    abstract = {This paper presents a study focused on advancing Automatic Speech Recognition (ASR) for the under-resourced language D{\"e}n{\"e} S{\k{u}}{\l}{\i}n{\'e} through data-centric approaches. We explore multiple strategies to enhance the quality of training data{---}both audio recordings and transcriptions{---}to address the challenges posed by mixed-quality datasets. Our experiments investigate which data preparation techniques most effectively improve ASR performance in this context. Our findings show that reducing non-phonemic spelling variation in the corpus significantly improves model generalization, resulting in a substantial increase in recognition accuracy. Additionally, we demonstrate that increasing manually reviewed transcriptions consistently improves word and character error rates, while audio enhancement slightly reduces performance, highlighting the complex trade-offs in low-resource ASR development.}
}