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

Spectral pattern recognition of improved voice quality

H Rihkanen1, L Leinonen, T Hiltunen

  • 1Department of Otorhinolaryngology, Helsinki University Central Hospital, Finland.

Journal of Voice : Official Journal of the Voice Foundation
|December 1, 1994
PubMed
Summary

A self-organizing map accurately identified voice quality disorders by analyzing acoustic features. This neural network approach detected improvements in voice quality after surgery, correlating with expert perception.

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

Prognostic Value of Bcl-xL in Head and Neck Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis.

Journal of oral pathology & medicine : official publication of the International Association of Oral Pathologists and the American Academy of Oral Pathology·2026
Same author

Functional outcome of total knee replacement: a study protocol for a prospective, double-blinded, parallel-group randomized, clinical controlled trial of novel, personalized and conventional implants.

BMC musculoskeletal disorders·2019
Same author

Using big data to explore worldwide trends in objective sleep in the transition to adulthood.

Sleep medicine·2019
Same author

Newly isolated Nodularia phage influences cyanobacterial community dynamics.

Environmental microbiology·2016
Same author

Integrated model for providing tactical emergency medicine support (TEMS): analysis of 120 tactical situations.

Acta anaesthesiologica Scandinavica·2011
Same author

Pulsed-resource dynamics increase the asymmetry of antagonistic coevolution between a predatory protist and a prey bacterium.

Journal of evolutionary biology·2011

Area of Science:

  • Computational intelligence
  • Speech science
  • Biomedical engineering

Background:

  • Voice disorders, such as those from insufficient glottal closure, significantly impact quality of life.
  • Objective acoustic analysis is crucial for diagnosing and monitoring voice disorders.
  • Perceptual ratings by experts are the gold standard but can be subjective.

Purpose of the Study:

  • To apply a self-organizing map (SOM) for spectral pattern recognition of voice quality.
  • To correlate the SOM's analysis with expert perceptual ratings of voice samples.
  • To evaluate the SOM's ability to detect changes in voice quality, including post-operative improvements.

Main Methods:

  • Utilized a self-organizing map (SOM), a type of neural network, for spectral pattern recognition.

Related Experiment Videos

  • Analyzed voice samples (/a/ phonations) from 34 subjects (15 postsurgical, 19 controls).
  • Computed an acoustic feature map and determined sample locations relative to a normal reference, comparing distances with expert perceptual ratings.
  • Main Results:

    • SOM map locations corresponded directly to the degree of audible voice disorder.
    • Normal voice samples clustered near the normal reference on the map.
    • Dysphonic voice samples were located further from the normal reference, aligning with perceptual judgments.
    • The SOM detected perceived voice quality improvements in post-operative patient samples.

    Conclusions:

    • Self-organizing maps are effective tools for objective voice quality analysis.
    • SOMs can accurately differentiate between normal and disordered voices based on acoustic features.
    • This method shows promise for monitoring treatment efficacy and detecting subtle voice changes.