# Perceptual compensation for tonal context in self-supervised speech models

arXiv: https://arxiv.org/abs/2606.17835 · HTML: https://mlsanity.com/paper/2606.17835/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [Do self-supervised speech models develop human-like perception biases?](https://mlsanity.com/paper/2205.15819/) (2022)
- [Probing Acoustic Representations for Phonetic Properties](https://mlsanity.com/paper/2010.13007/) (2020)
- [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)
- [What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model](https://mlsanity.com/paper/2306.06524/) (2023)
- [A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models](https://mlsanity.com/paper/2408.13678/) (2024)
- [Effective Context in Neural Speech Models](https://mlsanity.com/paper/2505.22487/) (2025)
- [What do self-supervised speech models know about Dutch? Analyzing advantages of language-specific pre-training](https://mlsanity.com/paper/2506.00981/) (2025)
- [Perception of Phonological Assimilation by Neural Speech Recognition Models](https://mlsanity.com/paper/2406.15265/) (2024)
- [Word stress in self-supervised speech models: A cross-linguistic comparison](https://mlsanity.com/paper/2507.04738/) (2025)
- [Bigger is not Always Better: The Effect of Context Size on Speech Pre-Training](https://mlsanity.com/paper/2312.01515/) (2023)

## Abstract (arXiv)

This study examines the extent to which the wav2vec2.0 architecture exhibits evidence of compensation for phonological context. We conducted a pseudo-replication of a perceptional compensation experiment on Mandarin Chinese tones, and compared the embedding similarities and probing classifier outputs between a purely self-supervised pre-trained model and a model fine-tuned for Mandarin ASR. No evidence of compensation was found in the embedding similarities of the purely pre-trained model. Probing classifiers showed some evidence of compensation in addition to the expected layer-wise improvements in categorization, but failed to replicate human performance on isolated test syllables. Our findings contrast with previous reports of sensitivity to phonological structure emerging through pre-training alone, and suggest that supervised objectives may be necessary to encourage the abstraction of at least some types of phonological regularities.