@inproceedings{alam-tyers-2026-common,
    title = "Common Voice for {P}akistan: Developing an Open Speech Corpus for Low-Resource {P}akistani Languages",
    author = "Alam, Meesum  and
      Tyers, Francis",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/paragraph-normalization/2026.lrec-1.265/",
    doi = "10.63317/4r3mie85u8cq",
    pages = "3355--3359",
    abstract = "Pakistan is home to more than 70 languages out of which 30 languages are endangered. Most of Pakistani languages remain absent from modern speech and text technologies, with resources focused on Urdu and a few major tongues. Through Mozilla{'}s Open Multilingual Speech Fund, this paper documents one year project for the development of an open, community driven speech corpus for 39 indigenous languages of Pakistan. The dataset includes locally authored texts, daily life sentences, poetry, and folk songs to make a culturally balanced. The project not only supports Automatic Speech Recognition but also promote linguistic preservation and digital inclusion."
}