@inproceedings{conti-etal-2025-unheard,
    title = "The Unheard Alternative: Contrastive Explanations for Speech-to-Text Models",
    author = "Conti, Lina  and
      Fucci, Dennis  and
      Gaido, Marco  and
      Negri, Matteo  and
      Wisniewski, Guillaume  and
      Bentivogli, Luisa",
    editor = "Belinkov, Yonatan  and
      Mueller, Aaron  and
      Kim, Najoung  and
      Mohebbi, Hosein  and
      Chen, Hanjie  and
      Arad, Dana  and
      Sarti, Gabriele",
    booktitle = "Proceedings of the 8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.blackboxnlp-1.23/",
    pages = "398--414",
    ISBN = "979-8-89176-346-3",
    abstract = "Contrastive explanations, which indicate why an AI system produced one output (the target) instead of another (the foil), are widely recognized in explainable AI as more informative and interpretable than standard explanations. However, obtaining such explanations for speech-to-text (S2T) generative models remains an open challenge. Adopting a feature attribution framework, we propose the first method to obtain contrastive explanations in S2T by analyzing how specific regions of the input spectrogram influence the choice between alternative outputs. Through a case study on gender translation in speech translation, we show that our method accurately identifies the audio features that drive the selection of one gender over another."
}