@inproceedings{huaman-etal-2026-building,
    title = "Building Community-Centred {NLP} Resources for {P}uno {Q}uechua",
    author = "Huaman, Elwin  and
      Gamarra Lafuente, Adrian  and
      Cordova, Johanna  and
      Korhonen, Anna",
    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-6.13/",
    pages = "147--152",
    ISBN = "979-8-89176-415-6",
    abstract = "The preservation of under-resourced languages requires digital tools and resources shaped by and for their speakers. We present the first dedicated ASR resources for Puno Quechua (ISO 639-3: qxp): (1) the largest speech corpus for any single Quechua variety, consisting in 66 hours of recordings for scripted and spontaneous speech (including 36 hours of manually transcribed and validated data), collected via a participatory design campaign; (2) the first systematic ASR benchmark for Puno Quechua, evaluating state-of-the-art models and fine-tuning Whisper-base, wav2vec2-base, and XLS-R-300M, with and without continued pre-training (CPT); (3) an open release of all datasets and fine-tuned models."
}