# Human-like Linguistic Biases in Neural Speech Models: Phonetic Categorization and Phonotactic Constraints in Wav2Vec2.0

arXiv: https://arxiv.org/abs/2407.03005 · HTML: https://mlsanity.com/paper/2407.03005/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 10 of 10)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (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 phonology in a recurrent neural model of grounded speech](https://mlsanity.com/paper/1706.03815/) (2017)
- [DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers](https://mlsanity.com/paper/2310.03686/) (2023)
- [Wave to Syntax: Probing spoken language models for syntax](https://mlsanity.com/paper/2305.18957/) (2023)
- [Analyzing analytical methods: The case of phonology in neural models of spoken language](https://mlsanity.com/paper/2004.07070/) (2020)
- [Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers](https://mlsanity.com/paper/2310.09925/) (2023)
- [Successes and critical failures of neural networks in capturing human-like speech recognition](https://mlsanity.com/paper/2204.03740/) (2022)

## Built on by (most cited first, 19 of 19)

- [How Linguistics Learned to Stop Worrying and Love the Language Models](https://mlsanity.com/paper/2501.17047/) (2025)
- [Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces](https://mlsanity.com/paper/2603.12642/) (2026)
- [Exploring bat song syllable representations in self-supervised audio encoders](https://mlsanity.com/paper/2409.12634/) (2024)
- [What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training](https://mlsanity.com/paper/2506.00981/) (2025)
- [Trick or Neat: Adversarial Ambiguity and Language Model Evaluation](https://mlsanity.com/paper/2506.01205/) (2025)
- [Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks](https://mlsanity.com/paper/2601.18617/) (2026)
- [Automatic classification of stop realisation with wav2vec2.0](https://mlsanity.com/paper/2505.23688/) (2025)
- [From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models](https://mlsanity.com/paper/2506.01133/) (2025)
- [The Curious Case of Visual Grounding: Different Effects for Speech- and Text-based Language Encoders](https://mlsanity.com/paper/2509.15837/) (2025)
- [Tracking the emergence of linguistic structure in self-supervised models learning from speech](https://mlsanity.com/paper/2604.02043/) (2026)
- [Language models as tools for investigating the distinction between possible and impossible natural languages](https://mlsanity.com/paper/2512.09394/) (2025)
- [Large language models have learned to use language](https://mlsanity.com/paper/2512.12447/) (2025)
- [Large language models are not about natural language](https://mlsanity.com/paper/2512.13441/) (2025)
- [Linguists should learn to love speech-based deep learning models](https://mlsanity.com/paper/2512.14506/) (2025)
- [Are Language Models Models?](https://mlsanity.com/paper/2601.10421/) (2026)
- [Across the Levels of Analysis: Explaining Predictive Processing in Humans Requires More Than Machine-Estimated Probabilities](https://mlsanity.com/paper/2604.09466/) (2026)
- [You Can't Fight in Here! This is BBS!](https://mlsanity.com/paper/2604.09501/) (2026)
- [Not-So-Strange Love: Language Models and Generative Linguistic Theories are More Compatible than They Appear](https://mlsanity.com/paper/2605.10061/) (2026)
- [Perceptual compensation for tonal context in self-supervised speech models](https://mlsanity.com/paper/2606.17835/) (2026)

## Abstract (arXiv)

What do deep neural speech models know about phonology? Existing work has examined the encoding of individual linguistic units such as phonemes in these models. Here we investigate interactions between units. Inspired by classic experiments on human speech perception, we study how Wav2Vec2 resolves phonotactic constraints. We synthesize sounds on an acoustic continuum between /l/ and /r/ and embed them in controlled contexts where only /l/, only /r/, or neither occur in English. Like humans, Wav2Vec2 models show a bias towards the phonotactically admissable category in processing such ambiguous sounds. Using simple measures to analyze model internals on the level of individual stimuli, we find that this bias emerges in early layers of the model's Transformer module. This effect is amplified by ASR finetuning but also present in fully self-supervised models. Our approach demonstrates how controlled stimulus designs can help localize specific linguistic knowledge in neural speech models.