@inproceedings{luthra-etal-2026-spidr,
    title = "{S}pid{R}-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation",
    author = "Luthra, Mahi  and
      Shen, Jiayi  and
      Poli, Maxime  and
      Tandazo, Angelo Ortiz  and
      Higuchi, Yosuke  and
      Benchekroun, Youssef  and
      Gleize, Martin  and
      Saint-James, Charles-{\textbackslash}'Eric  and
      Lin, Dongyan  and
      Rust, Phillip  and
      Villar-Corrales, Angel  and
      Surya  and
      Stark, Vanessa  and
      Moritz, Rashel  and
      Pino, Juan  and
      LeCun, Yann  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://preview.aclanthology.org/ingest-acl/2026.acl-long.1325/",
    pages = "28705--28728",
    ISBN = "979-8-89176-390-6",
    abstract = "Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-supervised speech models. To address this gap, this paper introduces SpidR-Adapt for rapid adaptation of speech units to new languages using minimal unlabeled data. We cast such low-resource speech representation learning as a meta-learning problem and construct a multi-task adaptive pre-training (MAdaPT) protocol which formulates the adaptation process as a bi-level optimization framework. To enable scalable meta-training under this framework, we propose a novel heuristic solution, first-order bi-level optimization (FOBLO), avoiding heavy computation costs. Finally, we stabilize meta-training by using a robust initialization through interleaved supervision which alternates self-supervised and supervised objectives. Empirically, SpidR-Adapt achieves rapid gains in phonemic discriminability (ABX) and downstream spoken language modeling scores (sWUGGY, sBLIMP, tSC), surpassing in-domain toplines after training on less than 1h of target-language audio and delivering $100\times$ greater data efficiency than standard multi-task training.. These findings highlight a practical, architecture-agnostic path toward biologically inspired, data-efficient representations. We open-source the training code and model checkpoints at https://github.com/facebookresearch/spidr-adapt."
}