@inproceedings{oukid-etal-2026-puma,
    title = "{PUMA}: Projected Universal Multilingual {ASR} for Low-Resource Settings. Application to Diverse {A}frican Languages",
    author = "Oukid, Ilyes  and
      Faye, Bilal  and
      Azzag, Hanane  and
      Lebbah, Mustapha  and
      Boulahia, Said Yacine",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.17/",
    pages = "371--382",
    ISBN = "979-8-89176-395-1",
    abstract = "Multilingual ASR systems often fail to generalize to low-resource and linguistically diverse languages while remaining costly to scale. We introduce PUMA, a unified multilingual ASR model that improves low-resource performance with reduced model complexity. PUMA employs a Universal Language Projection (ULP) module that integrates a learnable language token with acoustic representations, enabling language-aware processing through shared parameters. Experiments on diverse African languages show consistent word error rate reductions over strong multilingual baselines, highlighting improved robustness and generalization. Our code is available at the following GitHub URL: https://github.com/ilyes-okd/PUMA"
}