# Probing Acoustic Representations for Phonetic Properties

arXiv: https://arxiv.org/abs/2010.13007 · HTML: https://mlsanity.com/paper/2010.13007/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2020.

## Built on by (most cited first, 26 of 26)

- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [What Do Self-Supervised Speech Models Know About Words?](https://mlsanity.com/paper/2307.00162/) (2023)
- [Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models](https://mlsanity.com/paper/2207.06867/) (2022)
- [Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech](https://mlsanity.com/paper/2210.11723/) (2022)
- [Automatic Pronunciation Assessment using Self-Supervised Speech Representation Learning](https://mlsanity.com/paper/2204.03863/) (2022)
- [Encoding of lexical tone in self-supervised models of spoken language](https://mlsanity.com/paper/2403.16865/) (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)
- [Orthogonality and isotropy of speaker and phonetic information in self-supervised speech representations](https://mlsanity.com/paper/2406.09200/) (2024)
- [Probing Speech Emotion Recognition Transformers for Linguistic Knowledge](https://mlsanity.com/paper/2204.00400/) (2022)
- [Quantifying Language Variation Acoustically with Few Resources](https://mlsanity.com/paper/2205.02694/) (2022)
- [What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis](https://mlsanity.com/paper/2401.17632/) (2024)
- [Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations](https://mlsanity.com/paper/2509.15655/) (2025)
- [Crossing the Species Divide: Transfer Learning from Speech to Animal Sounds](https://mlsanity.com/paper/2509.04166/) (2025)
- [Automated speech tools for helping communities process restricted-access corpora for language revival efforts](https://mlsanity.com/paper/2204.07272/) (2022)
- [A Comparative Study of Self-Supervised Speech Representations in Read and Spontaneous TTS](https://mlsanity.com/paper/2303.02719/) (2023)
- [Do Discrete Self-Supervised Representations of Speech Capture Tone Distinctions?](https://mlsanity.com/paper/2410.19935/) (2024)
- [Phone and speaker spatial organization in self-supervised speech representations](https://mlsanity.com/paper/2302.14055/) (2023)
- [A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speech](https://mlsanity.com/paper/2405.08237/) (2024)
- [Normalization through Fine-tuning: Understanding Wav2vec 2.0 Embeddings for Phonetic Analysis](https://mlsanity.com/paper/2503.04814/) (2025)
- [A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition](https://mlsanity.com/paper/2210.00367/) (2022)
- [MulCPred: Learning Multi-modal Concepts for Explainable Pedestrian Action Prediction](https://mlsanity.com/paper/2409.09446/) (2024)
- [Evaluating the Representation of Vowels in Wav2Vec Feature Extractor: A Layer-Wise Analysis Using MFCCs](https://mlsanity.com/paper/2508.17914/) (2025)
- [An Entropy-Guided Curriculum Learning Strategy for Data-Efficient Acoustic Scene Classification under Domain Shift](https://mlsanity.com/paper/2509.11168/) (2025)
- [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)

Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited. But little is known about what phonetic properties these various representations acquire, and how well they encode transferable features of speech. We compare features from two conventional and four pre-trained systems in some simple frame-level phonetic classification tasks, with classifiers trained on features from one version of the TIMIT dataset and tested on features from another. All contextualized representations offered some level of transferability across domains, and models pre-trained on more audio data give better results; but overall, DeCoAR, the system with the simplest architecture, performs best. This type of benchmarking analysis can thus uncover relative strengths of various proposed acoustic representations.