@inproceedings{beccaria-etal-2026-automatic,
    title = "Automatic Detection of Direct and Self-Repetitions in Naturalistic Speech Recordings of {F}rench- and {D}utch-Speaking Autistic Children",
    author = "Beccaria, Federica  and
      Kolenberg, Marie  and
      Labendzki, Pierre  and
      Zink, Inge  and
      Kissine, Mikhail",
    editor = {Kokkinakis, Dimitrios  and
      Themistocleous, Charalambos  and
      Dias, Ga{\"e}l  and
      Fraser, Kathleen C.  and
      {\"O}hman, Fredrik  and
      Pais, Sebasti{\~a}o},
    booktitle = "Proceedings of the Sixth Resources and {P}rocess{I}ng of linguistic, para-linguistic and extra-linguistic Data from people with various forms of cognitive/psychiatric/developmental impairments in cooperation with the {MENTAL}.ai consortium",
    month = may,
    year = "2026",
    address = "Palma, Mallorca, Spain",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/cawl-year/2026.rapid-1.12/",
    doi = "10.63317/4eo4uey3z8kj",
    pages = "146--156",
    abstract = "This study investigates the use of cosine similarity measures across syntactic, lexical, and semantic vector repre- sentations to detect repetitions in the spontaneous speech of autistic children. It focuses on direct repetitions (i.e., immediate verbatim repetitions of linguistic output produced by another individual) and self-repetitions (i.e., within-speaker recurrence). The performance of similarity-based methods is then compared with state-of-the-art black-box classification models based on BERT, trained on the same data. Using spontaneous speech data from French- and Dutch- speaking autistic children, the results show that lexical and semantic similarity provide reliable cues for identifying self-repetitions, achieving high precision and recall, with F1-scores exceeding 83{\%}, comparable to those obtained by BERT-based models. In contrast, direct repetitions are more difficult to detect using similarity-based approaches, with BERT models clearly outperforming them and reaching F1-scores above 73{\%}. Across all conditions, syntactic similarity consistently underperforms relative to lexical and semantic measures. These findings highlight the strengths and limitations of similarity-based approaches and suggest directions for future research, particularly in improving the detection of direct repetitions and assessing the cross-linguistic generalizability of these methods."
}