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 Video

Updated: Jul 10, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Nonlinear dynamic neural network for text-independent speaker identification using information theoretic learning

Bing Lu1, Walter M Yamada, Theodore W Berger

  • 1Dept. of Biomed. Eng., Univ. of Southern California, Los Angeles, CA 90089, USA. blu@usc.edu

Conference Proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
|October 20, 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

PDI-Based Organic Small Molecule Regulated by Inter/Intramolecular Interactions for Efficient Solar Vapor Generation.

Small (Weinheim an der Bergstrasse, Germany)·2023
Same author

Long-acting lenacapavir protects macaques against intravenous challenge with simian-tropic HIV.

EBioMedicine·2023
Same author

Nomogram of uveal melanoma as prediction model of metastasis risk.

Heliyon·2023
Same author

Dual-Responsive Drug-Delivery System Based on PEG-Functionalized Pillararenes Containing Disulfide and Amido Bonds for Cancer Theranostics.

Chembiochem : a European journal of chemical biology·2023
Same author

Discovery of MK-8768, a Potent and Selective mGluR2 Negative Allosteric Modulator.

ACS medicinal chemistry letters·2023
Same author

Common and distinct functional brain network abnormalities in adolescent, early-middle adult, and late adult major depressive disorders.

Psychological medicine·2023

This study introduces a novel nonlinear dynamic neural network for text-independent speaker recognition. The new model enhances distinctiveness among speakers and improves recognition accuracy without needing exact voice signatures.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Signal Processing

Background:

  • Speaker recognition systems typically rely on unique voice signatures.
  • Existing methods face challenges in text-independent scenarios and blind learning.
  • There is a need for robust speaker recognition that enhances inter-speaker distinctiveness.

Purpose of the Study:

  • To present a novel nonlinear dynamic neural network design for text-independent speaker recognition.
  • To improve recognition performance by leveraging dynamic neural properties.
  • To amplify the distinctiveness between different speakers.

Main Methods:

  • Utilizing a nonlinear high-order synaptic neural model with memory.
  • Implementing the dynamic neural network in the short-term-frequency long-term-temporal domain.

Related Experiment Videos

Last Updated: Jul 10, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

  • Employing an informatics metric for blind learning in the nonlinear network.

    • Main Results:

    • The proposed network demonstrates improved text-independent speaker recognition.
    • The model successfully amplifies distinctiveness among speakers.
    • The use of dynamic properties and memory enhances recognition accuracy.

    Conclusions:

    • The novel nonlinear dynamic neural network offers a promising approach for text-independent speaker recognition.
    • This design overcomes limitations of traditional methods by incorporating dynamic and temporal information.
    • The study highlights the potential of advanced neural network architectures in enhancing biometric security.