# Exploiting Speech LLM Representations for Multilingual and Cross-Lingual Parkinson's Disease Detection

arXiv: https://arxiv.org/abs/2609.14431 · HTML: https://mlsanity.com/paper/2609.14431/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in ASR evaluation, bias and atypical speech, one of 11 directions in Speech and audio language models.
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Placed in

- Speech and audio language models / [ASR evaluation, bias and atypical speech](https://mlsanity.com/speech/asr-evaluation-bias-and-atypical-speech/)

## Builds on (most cited first, 17 of 17)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [Do Audio LLMs Really LISTEN, or Just Transcribe? Measuring Lexical vs. Acoustic Emotion Cues Reliance](https://mlsanity.com/paper/2510.10444/) (2025)
- [Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions](https://mlsanity.com/paper/2406.16128/) (2024)
- [Unveiling Interpretability in Self-Supervised Speech Representations for Parkinson's Diagnosis](https://mlsanity.com/paper/2412.02006/) (2024)
- [Speech Foundation Model Ensembles for the Controlled Singing Voice Deepfake Detection (CtrSVDD) Challenge 2024](https://mlsanity.com/paper/2409.02302/) (2024)
- [Probing Whisper for Dysarthric Speech in Detection and Assessment](https://mlsanity.com/paper/2510.04219/) (2025)
- [Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease](https://mlsanity.com/paper/2603.22225/) (2026)
- [ERM-MinMaxGAP: Benchmarking and Mitigating Gender Bias in Multilingual Multimodal Speech-LLM Emotion Recognition](https://mlsanity.com/paper/2603.21050/) (2026)
- [Paralinguistic Emotion-Aware Validation Timing Detection in Japanese Empathetic Spoken Dialogue](https://mlsanity.com/paper/2603.09307/) (2026)
- [Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language Models](https://mlsanity.com/paper/2605.24806/) (2026)

## Abstract (arXiv)

Speech Large Language Models (Speech LLMs) have shown strong performance across diverse tasks, yet their utility for pathological speech analysis remains underexplored. In this work, we investigate the effectiveness of internal representations from encoder and decoder components of Speech LLMs for Parkinson's Disease (PD) detection across multilingual and cross-lingual settings. Our findings reveal that encoder representations consistently outperform their decoder counterparts in most models and settings and that pathological cues may be progressively attenuated as audio representations are projected into the language model space. We further show that generative outputs are less reliable for clinical tasks compared to internal representations. To leverage information spread across multiple layers, we propose a Squeeze-and-Excitation (SE)-based dynamic layer aggregation framework, which surpasses best-layer selection in multiple experiments, suggesting that PD-relevant acoustic cues are distributed across transformer layers rather than concentrated in one.