MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery

[📜 arXiv] · [📖 ACL Anthology] · [🖋️ BibTeX]

This repository contains the data processing and training code for the MauBERT paper.

Overview

The HuBERT backbone is exposed as HuBERT. Two task-specific models build on top of it:

• MauBERT-feat: predicts phonetic features per frame (the fr task).
• MauBERT-phone: predicts IPA phone tokens per frame (the pr task).

Each model owns a HuBERT instance as an attribute, so the backbone can be frozen, fine-tuned, or weighted-summed across layers.

Citation

@inproceedings{ortiztandazo-etal-2026-maubert,
    title = "{M}au{BERT}: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery",
    author = "Ortiz Tandazo, Angelo  and
      Khentout, Manel  and
      Benchekroun, Youssef  and
      Hueber, Thomas  and
      Dupoux, Emmanuel",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.acl-long.24/",
    pages = "568--585",
    ISBN = "979-8-89176-390-6",
}

Acknowledgments

S3PRL: https://github.com/s3prl/s3prl