@article{zanon-boito-etal-2026-stardrinks,
    title = "{S}tar{D}rinks: An {E}nglish and {K}orean Test Set for {SLU} Evaluation in a Drink Ordering Scenario",
    author = "Zanon Boito, Marcely  and
      Brun, Caroline  and
      Kim, Inyoung  and
      PROUX, Denys M.  and
      Ait-Mokhtar, Salah  and
      Lagos, Nikolaos  and
      Meunier, Jean-Luc  and
      Calapodescu, Ioan",
    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.453/",
    pages = "5749--5756",
    abstract = "LLMs and speech assistants are increasingly used for task-oriented interactions, yet their evaluation often relies on controlled scenarios that fail to capture the variability and complexity of real user requests. Drink ordering, for example, involves diverse named entities, drink types, sizes, customizations, and brand-specific terminology, as well as spontaneous speech phenomena such as hesitations and self-corrections. To address this gap, we introduce StarDrinks, a test set in English and Korean containing speech utterances features, transcriptions, and annotated slots. Our dataset supports speech-to-slots SLU, transcription-to-slots NLU, and speech-to-transcription ASR evaluation, providing a realistic benchmark for model robustness and generalization in a linguistically rich, real-world task."
}