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

An Automated System for Sound Localization Testing in Hearing-Impaired Listeners
07:52

An Automated System for Sound Localization Testing in Hearing-Impaired Listeners

Published on: March 13, 2026

A unified neural-network-based speaker localization technique.

G Arslan1, F A Sakarya

  • 1Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712-1084, USA. arslan@ece.utexas.edu

IEEE Transactions on Neural Networks
|February 6, 2008
PubMed
Summary

This study introduces a novel neural network for real-time speaker localization, effective for both near-field and far-field sound sources. The method achieves high accuracy, improving applications like video conferencing and acoustic echo cancellation.

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

Effect of caffeine on respiratory rate, recovery time, and brain wave activity during emergence from sevoflurane anaesthesia in rats.

Revista espanola de anestesiologia y reanimacion..·2025
Same author

Comparison of hemodynamic and respiratory outcomes between two surgical positions for percutaneous nephrolithotomy: a prospective, randomized clinical trial.

Actas urologicas espanolas·2023
Same author

V-NOTES hysterectomy under spinal anaesthesia: A pilot study.

Facts, views & vision in ObGyn·2022
Same author

Screening of 23 candidate genes by next-generation sequencing of patients with permanent congenital hypothyroidism: novel variants in TG, TSHR, DUOX2, FOXE1, and SLC26A7.

Journal of endocrinological investigation·2021
Same author

Hemopressin increases penicillin-induced epileptiform activity in rats.

Bratislavske lekarske listy·2020
Same author

A measuremental approach to calcaneal fractures.

European journal of trauma and emergency surgery : official publication of the European Trauma Society·2016

Area of Science:

  • Signal Processing
  • Acoustics
  • Machine Learning

Background:

  • Real-time speaker localization is crucial for applications like video conferencing and acoustic echo cancellation.
  • Existing neural network methods are often limited to either far-field or near-field scenarios and can be computationally demanding.
  • Speaker movement between near-field and far-field necessitates a versatile localization approach.

Purpose of the Study:

  • To develop a unified neural network-based technique for simultaneous wide-band and narrow-band speaker localization.
  • To address the limitations of existing methods by creating a technique applicable to both near-field and far-field sources.
  • To enable computationally efficient, real-time speaker tracking.

Main Methods:

  • Utilized a multilayer perceptron feedforward neural network architecture.

Related Experiment Videos

Last Updated: Jul 7, 2026

An Automated System for Sound Localization Testing in Hearing-Impaired Listeners
07:52

An Automated System for Sound Localization Testing in Hearing-Impaired Listeners

Published on: March 13, 2026

  • Engineered feature vectors by calculating normalized instantaneous cross-power spectrum samples between adjacent microphone pairs.
  • Developed a unified approach for source localization applicable across different signal bandwidths and source distances.

    • Main Results:

    • The proposed technique demonstrated accurate speaker localization capabilities.
    • Achieved an absolute localization error of less than 3.5 degrees under specific simulation conditions (20 dB SNR, 8000 Hz sampling rate).
    • Validated the method's effectiveness for both wide-band and narrow-band signals in near-field and far-field environments.

    Conclusions:

    • The developed unified neural network technique offers a robust solution for real-time speaker localization.
    • This method overcomes the limitations of previous approaches by handling diverse signal types and source locations.
    • The findings support the application of this technique in advanced audio processing systems.