Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jul 4, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Method Matters: Enhancing Voice-Based Depression Detection With a New Data Collection Framework.

Dan Vilenchik1, Julie Cwikel2, Yacov Ezra3

  • 1School of Electrical and Computer Engineering, Ben Gurion University of the Negev, POB 653, Beer Sheva 84105, Israel.

Depression and Anxiety
|May 30, 2025
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cultural Adaptation and One-Year Follow-Up of the Mom-to-Mom Program Among Minority Arab Bedouin Women: Addressing Postpartum Depression.

Journal of clinical medicine·2025
Same author

Prognostic Value of Pulmonary Hypertension as an Incidental Finding Detected by Echocardiography in Patients Without Known Cardiovascular or Pulmonary Diseases.

Journal of clinical medicine·2025
Same author

Gender Differences in Coping Strategies and Life Satisfaction Following Cognitive-Behavioral and Mindfulness-Based Intervention for Crohn's Disease: A Randomized Controlled Trial.

Journal of clinical medicine·2025
Same author

Adoption and Use of Telemedicine and Digital Health Services Among Older Adults in Light of the COVID-19 Pandemic: Repeated Cross-Sectional Analysis.

JMIR aging·2024
Same author

MolOptimizer: A Molecular Optimization Toolkit for Fragment-Based Drug Design.

Molecules (Basel, Switzerland)·2024
Same author

Predicting Churn in Online Games by Quantifying Diversity of Engagement.

Big data·2023
Same journal

Systematic Review and Exploratory Meta-Analysis of AI-Enabled and Digital Technology-Assisted Interventions for Dental Anxiety During Dental Treatment.

Depression and anxiety·2026
Same journal

Measurement of Serum Parameters Attributes the Therapeutic Effects of Music Therapy to Augmented Stress-Coping Ability and Diminished Systemic Inflammation.

Depression and anxiety·2026
Same journal

Differential Patterns of Social Attention and Memory Profiles in Depression: Evidence From Third-Person Social Interaction Processing.

Depression and anxiety·2026
Same journal

Associations Between Adverse Childhood Experiences and Prenatal Depression Mediated Through Family Communication in Chinese Pregnant Women: Causal Mediation Analysis.

Depression and anxiety·2026
Same journal

How Does Fertility Stress Influence Depressive Symptoms in Female Partners of Infertile Couples in China? A Parallel Mediation Analysis of Infertility Stigma and Family Function.

Depression and anxiety·2026
Same journal

Network and Factor Structure of Depression and Anxiety Symptoms in Telemental Healthcare Patients From Bangladesh: Evidence for Precision Mental Healthcare.

Depression and anxiety·2026
See all related articles
This summary is machine-generated.

This study introduces a novel voice analysis method for detecting depression, improving accuracy by combining acoustic features with a single self-report question. This approach offers a promising, noninvasive tool for early depression screening.

Area of Science:

  • Psychiatry
  • Computational Linguistics
  • Biomedical Engineering

Background:

  • Depression is a leading cause of global disability, with diagnosis often hindered by accessibility issues.
  • Current diagnostic methods like psychiatrist consultations or lengthy self-assessments present challenges for individuals experiencing symptoms.
  • Developing accessible, noninvasive, and reliable depression detection methods is a critical healthcare need.

Purpose of the Study:

  • To present a novel pipeline for depression detection using voice analysis.
  • To address challenges in depression detection, including data imbalance, label quality, and model generalizability.
  • To evaluate the efficacy of combining acoustic voice features with self-report measures for improved predictive accuracy.

Main Methods:

More Related Videos

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

Related Experiment Videos

Last Updated: Jul 4, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

  • Utilized a high-quality, high-depression-prevalence dataset from a specialized chronic pain clinic.
  • Employed a 3-fold cross-validation test on a 52-patient dataset.
  • Combined voice-only acoustic features with Subject Unit of Distress (SUDs) self-report data.

Main Results:

  • Achieved a lift in accuracy of up to 15% over a 50-50 baseline (p-value 0.01).
  • Demonstrated that combining acoustic features with SUDs significantly improved predictive accuracy from 86% to 92% (p-value 0.1).
  • Showcased robust depression detection capabilities even with a limited sample size.

Conclusions:

  • The novel pipeline effectively addresses critical challenges in voice-based depression detection.
  • Combining acoustic voice features with SUDs offers a highly accurate and reliable method for depression detection.
  • This approach supports the development of rapid, noninvasive depression detection tools applicable across clinical settings.