# Tracking the emergence of linguistic structure in self-supervised models learning from speech

arXiv: https://arxiv.org/abs/2604.02043 · HTML: https://mlsanity.com/paper/2604.02043/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 81 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 30 of 31)

- [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)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Advances in Pre-Training Distributed Word Representations](https://mlsanity.com/paper/1712.09405/) (2017)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs](https://mlsanity.com/paper/2309.07311/) (2023)
- [Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner](https://mlsanity.com/paper/1607.08723/) (2016)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [Language acquisition: do children and language models follow similar learning stages?](https://mlsanity.com/paper/2306.03586/) (2023)
- [Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration](https://mlsanity.com/paper/2306.06232/) (2023)
- [Do self-supervised speech models develop human-like perception biases?](https://mlsanity.com/paper/2205.15819/) (2022)
- [Encoding of lexical tone in self-supervised models of spoken language](https://mlsanity.com/paper/2403.16865/) (2024)
- [Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0](https://mlsanity.com/paper/2407.03005/) (2024)
- [Wave to Syntax: Probing spoken language models for syntax](https://mlsanity.com/paper/2305.18957/) (2023)
- [A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models](https://mlsanity.com/paper/2408.13678/) (2024)
- [Analyzing analytical methods: The case of phonology in neural models of spoken language](https://mlsanity.com/paper/2004.07070/) (2020)
- [Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment](https://mlsanity.com/paper/2502.07029/) (2025)
- [Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale](https://mlsanity.com/paper/2510.24963/) (2025)
- [DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon](https://mlsanity.com/paper/2206.11332/) (2022)
- [Emergent morpho-phonological representations in self-supervised speech models](https://mlsanity.com/paper/2509.22973/) (2025)
- [SpidR: Learning Fast and Stable Linguistic Units for Spoken Language Models Without Supervision](https://mlsanity.com/paper/2512.20308/) (2025)
- [Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations](https://mlsanity.com/paper/2509.15655/) (2025)
- [What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training](https://mlsanity.com/paper/2506.00981/) (2025)
- [What has LeBenchmark Learnt about French Syntax?](https://mlsanity.com/paper/2403.02173/) (2024)

## Built on by (most cited first, 1 of 1)

- [Deep Speech Representations Track Word Timing along a Low-Dimensional Circular Trajectory](https://mlsanity.com/paper/2610.16273/) (2026)

## Abstract (arXiv)

Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such structure emerge in model training? We study the encoding of a wide range of linguistic structures, across layers and intermediate checkpoints of six Wav2Vec2 and HuBERT models trained on spoken Dutch. We find that different levels of linguistic structure show notably distinct layerwise patterns as well as learning trajectories, which can partially be explained by differences in their degree of abstraction from the acoustic signal and the timescale at which information from the input is integrated. Moreover, we find that the level at which pre-training objectives are defined strongly affects both the layerwise organization and the learning trajectories of linguistic structures, with greater parallelism induced by higher-order prediction tasks (i.e. iteratively refined pseudo-labels).