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

Classification of Illness01:17

Classification of Illness

The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

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

Sort by
Same author

Classifying voice disorders for machine learning: a pilot study using the USVAC-C2025 diagnostic framework.

Frontiers in digital health·2026
Same author

Voice disorders classification using machine learning: a scoping review.

Frontiers in digital health·2026
Same author

Optimizing voice therapy interventions: the application of the principles of motor learning in clinical practice.

Current opinion in otolaryngology & head and neck surgery·2026
Same author

Comparison of Auditory Perceptual Ratings Between Australian and Cantonese Listeners on Normal and Disordered Voices.

Journal of voice : official journal of the Voice Foundation·2026
Same author

Auditory Steady-State Responses and the Effects of Interaural Decoherence and Presence of Vision.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Authors' Response to a Letter to the Editor.

Journal of voice : official journal of the Voice Foundation·2025

Related Experiment Video

Updated: Jul 9, 2026

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

Data-driven refinements for voice disorder classification: improving accuracy and generalisability.

Rijul Gupta1, Catherine Madill2, Craig Jin1

  • 1Computing and Audio Research Laboratory, School of Electrical and Computer Engineering, The University of Sydney, Sydney, NSW, Australia.

Frontiers in Digital Health
|July 8, 2026
PubMed
Summary

A new data-driven taxonomy, CarLab 2025, improves voice disorder classification accuracy by aligning with acoustic patterns. This approach enhances model generalisation compared to traditional clinical frameworks for voice AI.

Keywords:
acoustic featurescross-database generalisationdata-driven classificationmachine learningmulti-class classificationvoice disorders

Related Experiment Videos

Last Updated: Jul 9, 2026

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

Area of Science:

  • Artificial Intelligence
  • Speech Science
  • Computational Linguistics

Background:

  • Machine learning models for vocal pathology are limited by conventional clinical frameworks that do not align with acoustic patterns.
  • This mismatch creates a performance gap between multi-class and binary detection tasks in Voice AI.

Purpose of the Study:

  • To introduce a novel data-driven classification framework (CarLab 2025) for voice disorder classification.
  • To establish a more generalisable foundation for voice disorder classification by aligning with acoustic relationships.

Main Methods:

  • Developed CarLab 2025, a data-driven classification framework based on model confusion patterns.
  • Compared CarLab 2025 against clinical taxonomies (USVAC 2025, Compton 2022, da Silva Moura 2024, Za'im 2023) across vocal tasks, features, and models.
  • Evaluated in-domain performance, cross-database generalisation, multi-task learning, and data injection.

Main Results:

  • CarLab 2025 achieved superior in-domain classification accuracy (67.20%) compared to clinical frameworks (61.03%).
  • Models trained with structured taxonomies outperformed those with single-disorder labels for out-of-domain generalisation.
  • Diverse vocal task training improved cross-database performance; multi-task learning showed no advantage.

Conclusions:

  • The data-driven CarLab 2025 framework provides a baseline performance exceeding existing clinical frameworks.
  • Exposure to varied recording conditions is crucial for binary generalisation in voice AI.
  • Robust multi-class generalisation requires more diverse multi-source training data for vocal pathology detection.