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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Impact of overexpression of cytosolic isoform of O-acetylserine sulfhydrylase on soybean nodulation and nodule metabolome.

Scientific reports·2018
Same author

Heavy metal contents and enrichment characteristics of dominant plants in wasteland of the downstream of a lead-zinc mining area in Guangxi, Southwest China.

Ecotoxicology and environmental safety·2018
Same author

Quantitative Monitoring and Visualization of Hydrogen Sulfide In Vivo Using a Luminescent Probe Based on a Ruthenium(II) Complex.

Angewandte Chemie (International ed. in English)·2018
Same author

Accurate virial coefficients of gaseous krypton from state-of-the-art ab initio potential and polarizability of the krypton dimer.

The Journal of chemical physics·2018
Same author

Reversible colour change in leaves enhances pollinator attraction and reproductive success in Saururus chinensis (Saururaceae).

Annals of botany·2018
Same author

Downregulation of microRNA-9 increases matrix metalloproteinase-13 expression levels and facilitates osteoarthritis onset.

Molecular medicine reports·2017

Related Experiment Video

Updated: Jun 7, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Mental Health Diagnosis From Voice Data Using Convolutional Neural Networks and Vision Transformers.

Rafiul Islam1, Md Taimur Ahad2, Faruk Ahmed1

  • 14IR Research Cell, Daffodil International University, Dhaka, Bangladesh.

Journal of Voice : Official Journal of the Voice Foundation
|November 16, 2024
PubMed
Summary

Deep learning models integrating Convolutional Neural Networks and Vision Transformers accurately identify mental health conditions using voice analysis. This approach shows promise for advancing computer-aided mental well-being diagnosis.

Keywords:
Mental health diagnostics—Convolutional Neural Network—Vision Transformer—Voice analysis—Integrated model—Machine learning—Early detection—Mental stability

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

Related Experiment Videos

Last Updated: Jun 7, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

369
Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
05:51

Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury

Published on: May 15, 2016

9.0K

Area of Science:

  • Computational Linguistics
  • Psychiatry
  • Artificial Intelligence

Background:

  • Human voice characteristics can serve as indicators of mental health status.
  • Existing diagnostic methods for mental well-being can be enhanced through technological advancements.
  • The integration of advanced deep learning models offers new avenues for objective mental health assessment.

Purpose of the Study:

  • To investigate the efficacy of combining Convolutional Neural Networks and Vision Transformers for mental health identification through voice analysis.
  • To develop and evaluate a deep learning model for distinguishing between stable and unstable mental health conditions based on vocal biomarkers.
  • To contribute to the field of computer-aided diagnosis in mental health.

Main Methods:

  • Voice data from individuals with stable and unstable mental health conditions were collected from Bangladeshi mental health institutions.
  • A hybrid deep learning model, integrating Convolutional Neural Networks and Vision Transformers, was developed for voice analysis.
  • The model's performance was evaluated using metrics such as accuracy, precision, recall, and F1 score.

Main Results:

  • The proposed model achieved high performance, with an overall accuracy of 91%.
  • Specific performance metrics included precision of 92% for the "Unstable" category and 90% for the "Stable" category.
  • Recall reached 91% for the "Stable" category and 92% for the "Unstable" category, with an F1 score of 91%.

Conclusions:

  • The integration of Convolutional Neural Networks and Vision Transformers in voice analysis demonstrates significant potential for accurate mental health identification.
  • Deep learning models offer a promising tool for computer-aided diagnosis, improving the objectivity and accessibility of mental well-being assessments.
  • This research highlights the substantial impact of deep learning on advancing mental health care and diagnosis.