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 Videos

Telephony-based voice pathology assessment using automated speech analysis.

Rosalyn J Moran1, Richard B Reilly, Philip de Chazal

  • 1Department of Electronic and Electrical Engineering, University College Dublin, Dublin 4, Ireland. rosalyn.moran@ee.ucd.ie

IEEE Transactions on Bio-Medical Engineering
|March 15, 2006
PubMed
Summary
This summary is machine-generated.

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

The Need for Demonstrated Clinical Translational Evidence in Submissions to the IEEE Journal of Translational Engineering in Health and Medicine.

IEEE journal of translational engineering in health and medicine·2026
Same author

Testing and tracking in the UK: A dynamic causal modelling study.

Wellcome open research·2026
Same author

Correction to: Ultra-low-field brain MRI morphometry: Test-retest reliability and correspondence to high-field MRI.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

VO2max ageing and all cause mortality in a global cohort of multi marathoners.

Scientific reports·2026
Same author

Comparison of oxygen desaturation area-based methods in predicting cardiovascular disease-related mortality outcomes.

Frontiers in network physiology·2026
Same author

Orthostatic hypotension without co-existent supine hypertension is associated with impaired cerebral oxygenation: findings from the Irish Longitudinal Study on Ageing (TILDA).

Journal of human hypertension·2026

This study developed a system to detect vocal fold pathologies using telephone speech. The system achieved 74.2% accuracy, with amplitude perturbation being a key feature for remote voice disorder diagnosis.

Area of Science:

  • Biomedical Engineering
  • Speech Science
  • Computational Linguistics

Background:

  • Vocal fold pathologies significantly impact communication.
  • Accurate remote diagnosis of voice disorders is challenging.
  • Existing diagnostic methods often require specialized equipment and clinical settings.

Purpose of the Study:

  • To develop and validate a system for remote detection of vocal fold pathologies using telephone-quality speech.
  • To assess the system's accuracy in classifying normal versus pathologic voices.
  • To subcategorize and identify specific types of voice pathologies remotely.

Main Methods:

  • Utilized a linear classifier trained on digitized speech recordings.
  • Extracted acoustic features including pitch perturbation, amplitude perturbation, and harmonic-to-noise ratio.

Related Experiment Videos

  • Validated the system using the Disordered Voice Database Model 4337.
  • Developed separate classifiers for subcategorizing pathologies (neuromuscular, physical, mixed).

    • Main Results:

    • The system achieved 89.1% accuracy for sustained phonation in controlled environments.
    • Telephone-quality speech classification yielded 74.2% accuracy.
    • Amplitude perturbation was identified as the most robust feature for telephone speech.
    • Remote detection accuracies for neuromuscular, physical, and mixed pathologies were 87%, 78%, and 61%, respectively.

    Conclusions:

    • Remote detection of vocal fold pathologies using telephone-quality speech is feasible.
    • The developed system demonstrates potential for accessible voice disorder screening.
    • Amplitude perturbation analysis is crucial for effective remote voice pathology assessment.