# Word stress in self-supervised speech models: A cross-linguistic comparison

arXiv: https://arxiv.org/abs/2507.04738 · HTML: https://mlsanity.com/paper/2507.04738/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 38 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## 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)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [What you can cram into a single vector: Probing sentence embeddings for linguistic properties](https://mlsanity.com/paper/1805.01070/) (2018)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Large-scale Self-Supervised Speech Representation Learning for Automatic Speaker Verification](https://mlsanity.com/paper/2110.05777/) (2021)
- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [Wave to Syntax: Probing spoken language models for syntax](https://mlsanity.com/paper/2305.18957/) (2023)
- [An Information-Theoretic Analysis of Self-supervised Discrete Representations of Speech](https://mlsanity.com/paper/2306.02405/) (2023)

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

- [Prosodic ABX: A Language-Agnostic Method for Measuring Prosodic Contrast in Speech Representations](https://mlsanity.com/paper/2604.02102/) (2026)
- [Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe](https://mlsanity.com/paper/2605.00607/) (2026)
- [Perceptual compensation for tonal context in self-supervised speech models](https://mlsanity.com/paper/2606.17835/) (2026)

## Abstract (arXiv)

In this paper we study word stress representations learned by self-supervised speech models (S3M), specifically the Wav2vec 2.0 model. We investigate the S3M representations of word stress for five different languages: Three languages with variable or lexical stress (Dutch, English and German) and two languages with fixed or demarcative stress (Hungarian and Polish). We train diagnostic stress classifiers on S3M embeddings and show that they can distinguish between stressed and unstressed syllables in read-aloud short sentences with high accuracy. We also tested language-specificity effects of S3M word stress. The results indicate that the word stress representations are language-specific, with a greater difference between the set of variable versus the set of fixed stressed languages.