Innovative Speech-Based Deep Learning Approaches for Parkinson's Disease Classification: A Systematic Review

L van Gelderen, C Tejedor-García - arXiv preprint arXiv:2407.17844, 2024 - arxiv.org
Parkinson's disease (PD), the second most prevalent neurodegenerative disorder
worldwide, frequently presents with early-stage speech impairments. Recent advancements …

Addressing challenges in speaker anonymization to maintain utility while ensuring privacy of pathological speech

S Tayebi Arasteh, T Arias-Vergara… - Communications …, 2024 - nature.com
Background Integration of speech into healthcare has intensified privacy concerns due to its
potential as a non-invasive biomarker containing individual biometric information. In …

The effect of speech pathology on automatic speaker verification: a large-scale study

S Tayebi Arasteh, T Weise, M Schuster, E Noeth… - Scientific Reports, 2023 - nature.com
Navigating the challenges of data-driven speech processing, one of the primary hurdles is
accessing reliable pathological speech data. While public datasets appear to offer solutions …

Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy

ST Arasteh, M Lotfinia, T Nolte, M Saehn… - arXiv preprint arXiv …, 2023 - arxiv.org
Developing robust and effective artificial intelligence (AI) models in medicine requires
access to large amounts of patient data. The use of AI models solely trained on large multi …

Enhancing domain generalization in the AI-based analysis of chest radiographs with federated learning

S Tayebi Arasteh, C Kuhl, MJ Saehn, P Isfort… - Scientific Reports, 2023 - nature.com
Developing robust artificial intelligence (AI) models that generalize well to unseen datasets
is challenging and usually requires large and variable datasets, preferably from multiple …

Exploring federated learning for speech-based parkinson's disease detection

A Sarlas, A Kalafatelis, G Alexandridis… - Proceedings of the 18th …, 2023 - dl.acm.org
Parkinson's Disease is the second most prevalent neurodegenerative disorder, currently
affecting as high as 3% of the global population. Research suggests that up to 80% of …

Mind the Gap: Federated Learning Broadens Domain Generalization in Diagnostic AI Models

ST Arasteh, C Kuhl, MJ Saehn, P Isfort, D Truhn… - arXiv preprint arXiv …, 2023 - arxiv.org
Developing robust artificial intelligence (AI) models that generalize well to unseen datasets
is challenging and usually requires large and variable datasets, preferably from multiple …

[HTML][HTML] Analyzing Wav2Vec 1.0 Embeddings for Cross-Database Parkinson's Disease Detection and Speech Features Extraction

O Klempíř, R Krupička - Sensors, 2024 - mdpi.com
Advancements in deep learning speech representations have facilitated the effective use of
extensive unlabeled speech datasets for Parkinson's disease (PD) modeling with minimal …

Parkinson's Disease Detection Based on Vocal Biomarkers and Machine Learning Approach

A Alrosan, M Abdel-Aty, M Hafez… - 2024 International …, 2024 - ieeexplore.ieee.org
Parkinson's disease (PD) must be identified early to provide prompt treatment and better
patient outcomes. This study looks into using machine learning methods in conjunction with …

The Impact of Speech Anonymization on Pathology and Its Limits

ST Arasteh, T Arias-Vergara, PA Pérez-Toro… - arXiv preprint arXiv …, 2024 - arxiv.org
Integration of speech into healthcare has intensified privacy concerns due to its potential as
a non-invasive biomarker containing individual biometric information. In response, speaker …