@article{shurtz-etal-2026-mekongphon,
    title = "{M}ekong{P}hon: A Large-Scale Parallel {IPA} Corpus for {L}ao and {K}hmer",
    author = "Shurtz, Ammon  and
      Richardson, Christian  and
      Richardson, Stephen D.",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.129/",
    pages = "1650--1658",
    abstract = "High-quality International Phonetic Alphabet (IPA) transcriptions are a foundational resource for speech and language technologies, yet existing tools for many low-resource languages remain limited in accuracy and scope. In this work, we present MekongPhon, a large-scale, high-quality parallel IPA corpus for Lao and Khmer. The corpus contains 1.3 million Khmer and 367 thousand Lao orthographic{--}IPA pairs, meticulously aligned and verified. When used to train Transformer-based sequence-to-sequence models, MekongPhon enables exceptionally accurate IPA generation, achieving under 2{\%} Character Error Rate (CER) on held-out test sets. We further introduce linguistically informed Lao and Khmer transliteration tools that offer high-speed IPA conversion, outperforming Epitran by 6-71 CER points despite trading some accuracy for efficiency. All data, code, and pretrained models are publicly released to support future research and development in low-resource language technologies."
}