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

arXiv: https://arxiv.org/abs/2508.21210 · HTML: https://mlsanity.com/paper/2508.21210/

## 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 (most cited first, 15 of 15)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [A Large-Scale Evaluation of Speech Foundation Models](https://mlsanity.com/paper/2404.09385/) (2024)
- [BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language models](https://mlsanity.com/paper/2306.01506/) (2023)
- [Do self-supervised speech models develop human-like perception biases?](https://mlsanity.com/paper/2205.15819/) (2022)
- [Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Models](https://mlsanity.com/paper/2210.16043/) (2022)
- [Investigating Critical Period Effects in Language Acquisition through Neural Language Models](https://mlsanity.com/paper/2407.19325/) (2024)
- [An open-source voice type classifier for child-centered daylong recordings](https://mlsanity.com/paper/2005.12656/) (2020)
- [Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition](https://mlsanity.com/paper/2502.04795/) (2025)
- [Perceptimatic: A human speech perception benchmark for unsupervised subword modelling](https://mlsanity.com/paper/2010.05961/) (2020)
- [A phonetic model of non-native spoken word processing](https://mlsanity.com/paper/2101.11332/) (2021)

## 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.