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

Speaker verification using committee neural networks.

Narender P Reddy1, Ojas A Buch

  • 1Biomedical Engineering Department, Human Interface and Medical Informatics Laboratory, University of Akron, Akron, OH 44325-0302, USA. npreddy@uakron.edu

Computer Methods and Programs in Biomedicine
|August 28, 2003
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

Gene expression based leukemia sub-classification using committee neural networks.

Bioinformatics and biology insights·2010
Same author

Facial expression (mood) recognition from facial images using committee neural networks.

Biomedical engineering online·2009
Same author

Toward a fuzzy logic control of the infant incubator.

Annals of biomedical engineering·2009
Same author

Neural network committees for finger joint angle estimation from surface EMG signals.

Biomedical engineering online·2009
Same author

Toward direct biocontrol using surface EMG signals: control of finger and wrist joint models.

Medical engineering & physics·2006
Same author

Fractal analysis of acceleration signals from patients with CPPD, rheumatoid arthritis, and spondyloarthroparthy of the finger joint.

Computer methods and programs in biomedicine·2005
Same journal

SynTME: A tumor microenvironment-aware, pharmacology-inspired multi-stage framework for drug synergy prediction.

Computer methods and programs in biomedicine·2026
Same journal

MMFVS-Net: A triple-symmetric cross-attention network for multimodal optical image fusion and high-accuracy virtual staining of breast cancer tissues.

Computer methods and programs in biomedicine·2026
Same journal

A novel Milstein-stochastic epidemiologically-informed neural network for approaching epidemic dynamics: Application to Mpox disease.

Computer methods and programs in biomedicine·2026
Same journal

Accounting for approximation errors using surrogate-based parameter estimation of cardiac mechanics digital twins.

Computer methods and programs in biomedicine·2026
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
See all related articles

This study developed a committee neural network for speech-based speaker verification. The committee achieved 100% accuracy in identifying speakers and rejecting imposters, enhancing voice security.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Signal Processing

Background:

  • Web-based and remote database access face significant security challenges.
  • Speaker verification is crucial for secure authentication in various applications.

Purpose of the Study:

  • To develop and evaluate a committee neural network technique for robust speech-based speaker verification.
  • To assess the effectiveness of combining multiple neural networks for improved speaker identification accuracy.

Main Methods:

  • Speech data from a designated speaker and imposters were collected.
  • Time and frequency domain parameters were extracted from speech samples.
  • Multiple neural networks were trained, and the top five formed a committee using majority voting.

Related Experiment Videos

Main Results:

  • The committee correctly identified the designated speaker in 100% of test cases (50/50).
  • The committee successfully rejected all imposters in 100% of test cases (150/150).
  • The committee's final decision was not unanimous in most tested instances.

Conclusions:

  • Committee neural networks offer a highly effective solution for speech-based speaker verification.
  • This approach significantly enhances security for voice-based access systems.
  • The method demonstrates strong potential for real-world speaker authentication applications.