mlsanityData to 14 Oct 2026

Do Self-Supervised Speech Models Exhibit the Critical Period Effects in Language Acquisition?

arXiv 2508.21210 ↗First posted 28 Aug 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper investigates whether the Critical Period (CP) effects in human language acquisition are observed in self-supervised speech models (S3Ms). CP effects refer to greater difficulty in acquiring a second language (L2) with delayed L2 exposure onset, and greater retention of their first language (L1) with delayed L1 exposure offset. While previous work has studied these effects using textual language models, their presence in speech models remains underexplored despite the central role of spoken language in human language acquisition. We train S3Ms with varying L2 training onsets and L1 training offsets on child-directed speech and evaluate their phone discrimination performance. We find that S3Ms do not exhibit clear evidence of either CP effects in terms of phonological acquisition. Notably, models with delayed L2 exposure onset tend to perform better on L2 and delayed L1 exposure offset leads to L1 forgetting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 28 Aug 2025.

Builds on

15 of 34 references.

References · 15

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  5. 2018Experience Replay for Continual Learningcited by 1,095
  6. 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 298
  7. 2024A Large-Scale Evaluation of Speech Foundation Modelscited by 40
  8. 2023BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language modelscited by 29
  9. 2022Do self-supervised speech models develop human-like perception biases?cited by 28
  10. 2022Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Modelscited by 21
  11. 2024Investigating Critical Period Effects in Language Acquisition through Neural Language Modelscited by 16
  12. 2020An open-source voice type classifier for child-centered daylong recordingscited by 14
3 more
  1. 2025Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisitioncited by 10
  2. 2020Perceptimatic: A human speech perception benchmark for unsupervised subword modellingcited by 6
  3. 2021A phonetic model of non-native spoken word processingcited by 5

Built on by

Not cited yet.