@inproceedings{bozik-suppa-2026-slopal,
    title = "{S}lo{P}al: A 60-Million-Word {S}lovak Parliamentary Corpus with Aligned Speech and Fine-Tuned {ASR} Models",
    author = "Bo{\v{z}}{\'i}k, Erik  and
      Suppa, Marek",
    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-1.282/",
    doi = "10.63317/3wovntemmb6u",
    pages = "3523--3533",
    abstract = "Slovak remains a low-resource language for automatic speech recognition (ASR), with fewer than 100 hours of publicly available training data. We present SloPal, a comprehensive Slovak parliamentary corpus comprising 330,000 speaker-segmented transcripts (66 million words, 220 million tokens) spanning 2001{--}2024, with rich metadata including speaker names, roles, and session information. From this collection, we derive SloPalSpeech, a 2,806-hour aligned speech dataset with segments up to 30 seconds, constructed using a language-agnostic anchor-based alignment pipeline and optimized for Whisper-based ASR training. Fine-tuning Whisper on SloPalSpeech reduces Word Error Rate (WER) by up to 70{\%}, with the fine-tuned small model (244M parameters) approaching base large-v3 (1.5B parameters) performance at 6$\times$ fewer parameters. We publicly release the SloPal text corpus, SloPalSpeech aligned audio, and four fine-tuned Whisper models at \url{https://huggingface.co/collections/NaiveNeuron/slopal}, providing the most comprehensive open Slovak parliamentary language resource to date."
}