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

Pathological voice quality assessment using artificial neural networks.

R T Ritchings1, M McGillion, C J Moore

  • 1Department of Computer Science, University of Salford, Salford, UK. t.ritchings@salford.ac.uk

Medical Engineering & Physics
|September 19, 2002
PubMed
Summary

This study developed an artificial neural network (ANN) system to objectively assess voice quality in laryngeal cancer patients. The system achieved 92% accuracy, aiding speech and language therapists in clinical voice evaluations.

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

Black Hole Spectroscopy and Tests of General Relativity with GW250114.

Physical review letters·2026
Same author

GW250114: Testing Hawking's Area Law and the Kerr Nature of Black Holes.

Physical review letters·2025
Same author

Search for Subsolar-Mass Binaries in the First Half of Advanced LIGO's and Advanced Virgo's Third Observing Run.

Physical review letters·2022
Same author

Constraints on Cosmic Strings Using Data from the Third Advanced LIGO-Virgo Observing Run.

Physical review letters·2021
Same author

A generative co-design framework for healthcare innovation: development and application of an end-user engagement framework.

Research involvement and engagement·2021
Same author

Prospects for observing and localizing gravitational-wave transients with Advanced LIGO, Advanced Virgo and KAGRA.

Living reviews in relativity·2020

Area of Science:

  • Speech and Hearing Sciences
  • Biomedical Engineering
  • Artificial Intelligence in Medicine

Background:

  • Laryngeal cancer treatment can significantly impair voice quality, necessitating objective assessment methods.
  • Subjective voice quality assessment by speech and language therapists (SALT) is crucial but can be variable.
  • Developing automated systems can provide consistent and objective voice analysis.

Purpose of the Study:

  • To create a prototype system for objective voice quality assessment in patients with laryngeal cancer.
  • To utilize artificial neural networks (ANNs) for analyzing voice parameters.
  • To support clinical decision-making by providing a reliable voice assessment tool.

Main Methods:

  • Collected electroglottography (EGG) signals from male subjects phonating the vowel /i/.

Related Experiment Videos

  • Extracted short-term and long-term time-domain and frequency-domain voice parameters.
  • Trained and tested multi-layer perceptron (MLP) artificial neural networks (ANNs) using these parameters.

    • Main Results:

    • The ANN system achieved 92% accuracy in objectively assessing voice quality.
    • A combination of short-term and long-term voice parameters yielded the best results.
    • The system demonstrated potential for reliable voice quality evaluation.

    Conclusions:

    • The developed ANN system shows promise as an objective tool for voice quality assessment in laryngeal cancer patients.
    • This system can serve as a valuable aid for speech and language therapists during clinical evaluations.
    • Further development could integrate this system into routine clinical practice for improved voice assessment.