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

Using genetic algorithms with subjective input from human subjects: implications for fitting hearing aids and

Deniz Başkent1, Cheryl L Eiler, Brent Edwards

  • 1Starkey Hearing Research Center, Berkeley, California 94704, USA. deniz_baskent@starkey.com

Ear and Hearing
|May 9, 2007
PubMed
Summary

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

Evolving the philosophy: from the NAL rule to NAL-NL3.

International journal of audiology·2026
Same author

The NAL-NL3 Fitting System.

International journal of audiology·2026
Same author

Implicit and Explicit Voice Training Effects on Speech-on-Speech Perception and Listening Effort.

Ear and hearing·2026
Same author

Music Ensemble: a large dataset on musicianship, cognition, and personality in musicians and nonmusicians.

Scientific data·2026
Same author

Exploring barriers to hearing help-seeking using behavioral economics: a qualitative study.

International journal of audiology·2025
Same author

Insights into current coccidioidomycosis therapeutic pathways.

Antimicrobial agents and chemotherapy·2025

Genetic algorithms (GA) effectively optimize hearing aid and cochlear implant settings using subjective user feedback. This approach provides good fitting solutions quickly, enhancing audiology device personalization.

Area of Science:

  • Audiology
  • Biomedical Engineering
  • Computational Intelligence

Background:

  • Individual hearing device fitting is complex due to varying user pathology and preferences.
  • Subjective user evaluation is crucial but challenging for systematic, quantitative algorithm assessment.
  • Optimization algorithms require methods to integrate listener input effectively.

Purpose of the Study:

  • To analyze the feasibility of using genetic algorithms (GA) for optimizing hearing aid and cochlear implant settings.
  • To evaluate GA performance driven solely by subjective human input in clinical or research settings.
  • To assess the efficiency and reliability of GA-driven hearing device fitting.

Main Methods:

  • An artificial listening environment was created using a noiseband vocoder to distort speech.

Related Experiment Videos

  • Nine normal-hearing subjects provided subjective preferences for sentence intelligibility.
  • Genetic algorithms iteratively adjusted parameters (vocoder channels, frequency shifts, compression) based on user feedback.
  • Objective speech recognition tests evaluated the GA-derived settings against optimal conditions.

    • Main Results:

    • GA successfully produced hearing device settings comparable to the best vocoder solutions.
    • Average convergence time for the GA was 25.5 minutes (8 iterations).
    • Settings from multiple GA runs showed slight variations but yielded similar speech recognition scores.
    • Subjective preferences generally aligned with objective speech intelligibility measures.

    Conclusions:

    • Genetic algorithms are feasible for optimizing hearing device fitting using listener preferences.
    • GA can achieve good fitting solutions efficiently, with an average convergence time of 25.5 minutes.
    • Enhancements for robustness (e.g., multiple runs) and speed (optimizing comparisons) are suggested for practical application.