This work investigates the effectiveness of internal representations from encoder and decoder components of Speech LLMs for Parkinson's Disease detection across multilingual and cross-lingual settings and proposes a Squeeze-and-Excitation (SE)-based dynamic layer aggregation framework, which surpasses best-layer selection in multiple experiments.
Abstract
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.
This work evaluates pre-trained embeddings from four state-of-the-art open-source SFMs across three datasets in zero-shot and k-shot cross-lingual settings for multi-class PD severity assessment and shows that pre-trained speech embeddings enable meaningful cross-lingual transfer, although performance is sensitive to d...
Simon Pals, Cristian Tejedor-García· arXiv.org· 0 citations
Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects speech and language abilities, making speech analysis a promising non-invasive tool for early screening and monitoring. Most existing speech-based AD detection systems are developed using single-language datasets and controlled recording...
Aman Singh, Dileep Kumar· International Journal of Dru...· 0 citations
CL-DAF is presented, a Cross-Lingual Disease-Alignment Framework that identifies acoustic dimensions whose disease effects remain consistent across languages and provides a foundation for multilingual clinical speech models emphasizing pathology over language-dependent variation.
Roksana Khanom, Raghib Asfak Tasnim, Bodrun Nahar Bithi et al.· arXiv.org· 0 citations
It is argued that intervention-based robustness tests should become standard for trustworthy clinical speech models and show that high predictive performance and the absence of a significant diagnostic-group difference in a measured acoustic factor are not sufficient for robustness.
Serli Kopar, Alkis Koudounas, R. Rane et al.· 0 citations
This study provides a scalable, objective, and explainable framework for speech-based cognitive screening, combining cognitive status classification with natural language explanations that clinicians can assess and verify, bridging the gap between advanced AI and clinical utility.
Zi-Yun Cui, Wen Wu, Chuan Shi et al.· arXiv.org· 0 citations
Automated Depression Detection (ADD) from speech aims to estimate an individual’s depression-related attributes using artificial intelligence applied to spoken signals. However, existing speech-based ADD methods rely on handcrafted acoustic features and high-resource language, which fail to capture clinically grounded...
Bubai Maji, Monorama Swain, Shazia Nasreen et al.· IEEE Transactions on Audio,...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.