@inproceedings{simonotti-etal-2026-say,
    title = "Say Again? The Limits of Whisper with Conversation. A Case Study on the {KIP}arla Corpus.",
    author = "Simonotti, Martina  and
      Pannitto, Ludovica  and
      Mauri, Caterina  and
      Ferraresi, Adriano  and
      Carioli, Gabriele",
    editor = "Hosseini-Kivanani, Nina  and
      Brutti, Alessio  and
      Matassoni, Marco  and
      Dowerah, Sandipana  and
      Liga, Davide  and
      Schommer, Christoph",
    booktitle = "Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis ({SPEAKABLE}) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/cawl-year/2026.speakable-1.3/",
    doi = "10.63317/2so5y449gb4w",
    pages = "16--30",
    abstract = "This study investigates how Whisper handles interactional phenomena in spontaneous Italian conversation, focusing on backchannels, repairs, and filled pauses. We compare standard Word Error Rate (WER) optimization with a decoding strategy that explicitly rewards the preservation of interactional events. Results show that decoding choices have limited impact on overall accuracy, while recognition remains strongly phenomenon-dependent, suggesting structural limitations in the handling of interactional phenomena, with systematic linearization of repairs and frequent suppression of short conversational items."
}