# Perception of Phonological Assimilation by Neural Speech Recognition Models

arXiv: https://arxiv.org/abs/2406.15265 · HTML: https://mlsanity.com/paper/2406.15265/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 75 references that are in the map.
- First posted on arXiv 21 Jun 2024.

## Builds on (most cited first, 12 of 12)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [Encoding of phonology in a recurrent neural model of grounded speech](https://mlsanity.com/paper/1706.03815/) (2017)
- [Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model](https://mlsanity.com/paper/2310.12611/) (2023)
- [Wave to Syntax: Probing spoken language models for syntax](https://mlsanity.com/paper/2305.18957/) (2023)
- [Causal interventions expose implicit situation models for commonsense language understanding](https://mlsanity.com/paper/2306.03882/) (2023)

## Built on by (most cited first, 3 of 3)

- [Trick or Neat: Adversarial Ambiguity and Language Model Evaluation](https://mlsanity.com/paper/2506.01205/) (2025)
- [Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yor`ub'a](https://mlsanity.com/paper/2604.07467/) (2026)
- [Perceptual compensation for tonal context in self-supervised speech models](https://mlsanity.com/paper/2606.17835/) (2026)

## Abstract (arXiv)

Human listeners effortlessly compensate for phonological changes during speech perception, often unconsciously inferring the intended sounds. For example, listeners infer the underlying /n/ when hearing an utterance such as "clea[m] pan", where [m] arises from place assimilation to the following labial [p]. This article explores how the neural speech recognition model Wav2Vec2 perceives assimilated sounds, and identifies the linguistic knowledge that is implemented by the model to compensate for assimilation during Automatic Speech Recognition (ASR). Using psycholinguistic stimuli, we systematically analyze how various linguistic context cues influence compensation patterns in the model's output. Complementing these behavioral experiments, our probing experiments indicate that the model shifts its interpretation of assimilated sounds from their acoustic form to their underlying form in its final layers. Finally, our causal intervention experiments suggest that the model relies on minimal phonological context cues to accomplish this shift. These findings represent a step towards better understanding the similarities and differences in phonological processing between neural ASR models and humans.