@article{klezovich-etal-2026-much,
    title = "How Much Data Is Enough Data? A New Motion Capture Corpus for Probabilistic Sign Language Generation",
    author = "Klezovich, Anna  and
      Mesch, Johanna  and
      Henter, Gustav Eje  and
      Beskow, Jonas",
    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.750/",
    pages = "9549--9558",
    abstract = "We present a new 4.1 hours long high-quality motion capture sign language dataset for Swedish Sign Language {---} STS Mocap v1. The dataset consists of high quality multimodal data: body tracked with markers, fingers tracked with Manus Quantum Metagloves, face tracked with iPhone LiveLink app in MetaHuman Animator mode, and corresponding textual sentence translation to spoken Swedish. With the help of this dataset, we show that four hours of motion capture data is enough for generative modeling of sign language conditioned on 2D pose. In comparison, training the same flow-matching model on only 30 minutes of this data, which is a common size for sign language motion capture datasets, shows a significant degradation in the quality of the synthesized data."
}