@inproceedings{kando-miyao-2026-learnability,
    title = "On the Learnability of Syntax from Raw Speech with Autoregressive Predictive Coding",
    author = "Kando, Shunsuke  and
      Miyao, Yusuke",
    editor = "Ma, Martin Ziqiao  and
      Liu, Emmy  and
      Liu, Jing  and
      Chang, Tyler A.  and
      Fourtassi, Abdellah  and
      Warstadt, Alex  and
      Hahn, Michael  and
      Sun, Weiwei  and
      Shi, Freda",
    booktitle = "Proceedings of the 1st Workshop on Computational Developmental Linguistics ({CDL})",
    month = jul,
    year = "2026",
    address = "Grand Hyatt Manchester San Diego, 1 Market Pl, San Diego, CA 92101",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.cdl-1.11/",
    pages = "77--82",
    ISBN = "979-8-89176-428-6",
    abstract = "Children are known to generalize syntactic knowledge at ages when their linguistic input is predominantly raw speech rather than text. This raises the question of whether syntactic generalization can emerge directly from acoustic input. We address this question using Autoregressive Predictive Coding (APC), a simple prediction-based self-supervised speech model. To approximate the input available to human learners while enabling controlled comparison, we train models on both child-directed speech and audiobook speech. We evaluate the models on a minimal-pair benchmark targeting elementary syntactic phenomena, designed to be acquisition-friendly. Our results show that APC partially generalizes word-order regularities when trained to predict near-future frames. However, the model fails to generalize agreement phenomena, suggesting that predictive learning from acoustic signals alone is insufficient. Furthermore, we observe distinct learning dynamics across word-order phenomena, suggesting that some improvements may be driven by shallow statistical regularities rather than genuine syntactic generalization."
}