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 7, 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

A modified HME architecture for text-dependent speaker identification.

K Chen1, D Xie, H Chi

  • 1Nat. Lab. of Machine Perception, Beijing Univ.

IEEE Transactions on Neural Networks
|January 1, 1996
PubMed
Summary

A new speaker identification system uses a modified hierarchical mixtures of experts (HME) architecture. This enhanced model improves accuracy by incorporating spectral information, outperforming the original HME approach.

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

The small-cage induced sedentariness in male young rats: evidence from energy expenditure and glucose uptake.

Scientific reports·2026
Same author

Tucatinib and trastuzumab emtansine for patients with previously treated HER2-positive locally advanced and metastatic breast cancer: primary analysis of the randomized phase III trial HER2CLIMB-02.

Annals of oncology : official journal of the European Society for Medical Oncology·2025
Same author

Multimodal imaging of a left anterior descending artery fistula with a dissecting interventricular septal aneurysm: a case report.

Hong Kong medical journal = Xianggang yi xue za zhi·2025
Same author

Short bouts and long-term exercise reduce sedentary-induced bone loss and microstructural changes by modulating bone formation and resorption in healthy young male rats.

Scientific reports·2025
Same author

Association between sedentary behavior and bone mass, microstructure and strength in children, adolescents and young adults: a systematic review.

BMC public health·2024
Same author

[A transcriptomic analysis of correlation between mitochondrial function and energy metabolism remodeling in mice with myocardial fibrosis following myocardial infarction].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2024

Area of Science:

  • Speech processing
  • Machine learning
  • Biometrics

Background:

  • Speaker identification is crucial for security and authentication.
  • Existing hierarchical mixtures of experts (HME) architectures have limitations in capturing dynamic speech features.
  • Text-dependent speaker identification requires models that can analyze specific utterance characteristics.

Purpose of the Study:

  • To introduce a modified hierarchical mixtures of experts (HME) architecture for text-dependent speaker identification.
  • To enhance speaker recognition by integrating instantaneous and transitional spectral information.
  • To develop an Expectation-Maximization (EM) algorithm for parameter optimization.

Main Methods:

  • A novel gating network was integrated into the HME architecture.

Related Experiment Videos

Last Updated: Jul 7, 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

  • A statistical model was developed for the modified HME.
  • Parameter learning was framed as a maximum likelihood problem, utilizing an EM algorithm.
  • The system was evaluated on a database of isolated digit utterances from 10 male speakers.

    • Main Results:

    • The modified HME architecture demonstrated superior performance compared to the original HME.
    • The inclusion of instantaneous and transitional spectral information improved identification accuracy.
    • The proposed EM algorithm effectively adjusted model parameters.

    Conclusions:

    • The modified HME architecture is effective for text-dependent speaker identification.
    • The novel gating network successfully utilizes spectral dynamics for improved recognition.
    • The proposed method offers a significant advancement in speaker identification technology.