# Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis

arXiv: https://arxiv.org/abs/2412.02006 · HTML: https://mlsanity.com/paper/2412.02006/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 86 references that are in the map.
- First posted on arXiv 2 Dec 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks](https://mlsanity.com/paper/2306.07303/) (2023)
- [Detecting Dysfluencies in Stuttering Therapy Using wav2vec 2.0](https://mlsanity.com/paper/2204.03417/) (2022)
- [TRILLsson: Distilled Universal Paralinguistic Speech Representations](https://mlsanity.com/paper/2203.00236/) (2022)
- [NeuroVoz: a Castillian Spanish corpus of parkinsonian speech](https://mlsanity.com/paper/2403.02371/) (2024)
- [Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues](https://mlsanity.com/paper/2401.02746/) (2024)
- [Multi-class Detection of Pathological Speech with Latent Features: How does it perform on unseen data?](https://mlsanity.com/paper/2210.15336/) (2022)

## Built on by (most cited first, 8 of 8)

- [Evaluating the Usefulness of Non-Diagnostic Speech Data for Developing Parkinson's Disease Classifiers](https://mlsanity.com/paper/2505.18722/) (2025)
- [RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification](https://mlsanity.com/paper/2507.03594/) (2025)
- [From Black Box to Biomarker: Sparse Autoencoders for Interpreting Speech Models of Parkinson's Disease](https://mlsanity.com/paper/2507.16836/) (2025)
- [The Role of Prosodic and Lexical Cues in Turn-Taking with Self-Supervised Speech Representations](https://mlsanity.com/paper/2601.13835/) (2026)
- [SAND: The Challenge on Speech Analysis for Neurodegenerative Disease Assessment](https://mlsanity.com/paper/2604.16445/) (2026)
- [A Benchmark for Early-stage Parkinson's Disease Detection from Speech](https://mlsanity.com/paper/2605.14066/) (2026)
- [Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention](https://mlsanity.com/paper/2606.09271/) (2026)
- [Cross-Lingual Parkinson's Disease Severity Assessment Using Pre-trained Speech Embeddings: A Multi-Class Evaluation](https://mlsanity.com/paper/2609.20875/) (2026)

## Abstract (arXiv)

Recent works in pathological speech analysis have increasingly relied on powerful self-supervised speech representations, leading to promising results. However, the complex, black-box nature of these embeddings and the limited research on their interpretability significantly restrict their adoption for clinical diagnosis. To address this gap, we propose a novel, interpretable framework specifically designed to support Parkinson's Disease (PD) diagnosis. Through the design of simple yet effective cross-attention mechanisms for both embedding- and temporal-level analysis, the proposed framework offers interpretability from two distinct but complementary perspectives. Experimental findings across five well-established speech benchmarks for PD detection demonstrate the framework's capability to identify meaningful speech patterns within self-supervised representations for a wide range of assessment tasks. Fine-grained temporal analyses further underscore its potential to enhance the interpretability of deep-learning pathological speech models, paving the way for the development of more transparent, trustworthy, and clinically applicable computer-assisted diagnosis systems in this domain. Moreover, in terms of classification accuracy, our method achieves results competitive with state-of-the-art approaches, while also demonstrating robustness in cross-lingual scenarios when applied to spontaneous speech production.