Article

Speech Foundation Models for Parkinson’s Disease Detection: A Layer-Wise Comparison with Handcrafted Acoustics Across Two Cohorts

2026-08-18

Abstract excerpt

<title>Abstract</title> <p>Foundation models have transformed speech processing, but their value for clinical voice analysis, particularly in Parkinson’s disease (PD), remains largely unexplored. In this study, we compare layer-wise representations from several foundation-model families (Whisper, Wav2Vec 2.0, OmniASR, NVIDIA Nemotron, and Qwen3-ASR) with a handcrafted acoustic baseline using sentence reading and...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: f831d47f-9b60-5a27-8367-2cf3dab79f50
DOI: 10.21203/rs.3.rs-10611782/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Speech Foundation Models for Parkinson’s Disease Detection: A Layer-Wise Comparison with Handcrafted Acoustics Across Two CohortsDOI 10.21203/rs.3.rs-10611782/v1Read

Ranking Pretrained Speech Embeddings in Parkinson’s Disease Detection: Does Wav2Vec 2.0 Outperform its 1.0 Version Across Speech Modes and Languages?Semantic proximity Read

Statistical, Multi-scale and Attention-based Layer Pooling of Wav2Vec-2 Speech Embeddings for Parkinson’s Disease DetectionSemantic proximity Read

Towards A Foundation Model for Clinical Voice BiomarkersSemantic proximity Read

Analyzing wav2vec embedding in Parkinson’s disease speech: A study on cross-database classification and regression tasksSemantic proximity Read

Speech-Based Parkinson's Detection Using Pre-Trained Self-Supervised Automatic Speech Recognition (ASR) Models and Supervised Contrastive LearningSemantic proximity Read

Normative Speech Modeling for ALS Diagnosis with Application to Other Neurodegenerative DiseasesSemantic proximity Read

Harnessing Voice Analysis and Machine Learning for Early Diagnosis of Parkinson's Disease: A Comparative Study Across Three DatasetsSemantic proximity Read

A Neural Speech Decoding Framework Leveraging Deep Learning and Speech SynthesisSemantic proximity Read

Explainable Artificial Intelligence to Diagnose Early Parkinson’s Disease via Voice AnalysisSemantic proximity Read

Automated Detection of Motor Speech Disorders and Subtype ClassificationSemantic proximity Read

An approach for Parkinson's disease detection based on Artificial Inteligence techniquesSemantic proximity Read

Performance-weighted ensemble learning for detecting patients with FTD and ALS from short reading tasksSemantic proximity Read