X-Vectors: New Quantitative Biomarkers for Early Parkinson's Disease Detection From Speech

Many articles have used voice analysis to detect Parkinson's disease (PD), but few have focused on the early stages of the disease and the gender effect. In this article, we have adapted the latest speaker recognition system, called x-vectors, in order to detect PD at an early stage using voice...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Frontiers in neuroinformatics Jg. 15; S. 578369 - 578369:18
Hauptverfasser: Jeancolas, Laetitia, Petrovska-Delacrétaz, Dijana, Mangone, Graziella, Benkelfat, Badr-Eddine, Corvol, Jean-Christophe, Vidailhet, Marie, Lehéricy, Stéphane, Benali, Habib
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland Frontiers Research Foundation 19.02.2021
Frontiers Media
Frontiers Media S.A
Schlagworte:
Alzheimer's disease
automatic detection
Classification
Computer Science
Decision trees
Discriminant analysis
early detection
Gender
Larynx
Life Sciences
Machine Learning
Movement disorders
Neural and Evolutionary Computing
Neural networks
Neurodegenerative diseases
Neurons and Cognition
Neuroscience
Parkinson's disease
Signal and Image Processing
Sound
Speech
Standard deviation
Support vector machines
telediagnosis
voice analysis
x-vectors
x-vectors
Parkinson's disease
telediagnosis
voice analysis
automatic detection
early detection
MFCC
deep neural networks
Deep neural networks
Telediagnosis
X-vectors
Voice analysis
Early detection
Automatic detection
ISSN:1662-5196, 1662-5196
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Many articles have used voice analysis to detect Parkinson's disease (PD), but few have focused on the early stages of the disease and the gender effect. In this article, we have adapted the latest speaker recognition system, called x-vectors, in order to detect PD at an early stage using voice analysis. X-vectors are embeddings extracted from Deep Neural Networks (DNNs), which provide robust speaker representations and improve speaker recognition when large amounts of training data are used. Our goal was to assess whether, in the context of early PD detection, this technique would outperform the more standard classifier MFCC-GMM (Mel-Frequency Cepstral Coefficients—Gaussian Mixture Model) and, if so, under which conditions. We recorded 221 French speakers (recently diagnosed PD subjects and healthy controls) with a high-quality microphone and via the telephone network. Men and women were analyzed separately in order to have more precise models and to assess a possible gender effect. Several experimental and methodological aspects were tested in order to analyze their impacts on classification performance. We assessed the impact of the audio segment durations, data augmentation, type of dataset used for the neural network training, kind of speech tasks, and back-end analyses. X-vectors technique provided better classification performances than MFCC-GMM for the text-independent tasks, and seemed to be particularly suited for the early detection of PD in women (7–15% improvement). This result was observed for both recording types (high-quality microphone and telephone).
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Edited by: Michel Dojat, Institut National de la Santé et de la Recherche Médicale (INSERM), France
Reviewed by: Maria L. Bringas, University of Electronic Science and Technology of China, China; Pedro Gomez-Vilda, Polytechnic University of Madrid, Spain; Alberto Mazzoni, Sant'Anna School of Advanced Studies, Italy
ISSN:1662-5196
1662-5196
DOI:10.3389/fninf.2021.578369