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 Concept Videos

Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Sociodemographic Correlates of Breast Cancer Screening Beliefs and Barriers Among Women in Kuwait: A Cross-Sectional Study Using the BCSBQ.

Healthcare (Basel, Switzerland)·2026
Same author

Cardiometabolic Mortality and Health System Expansion in Kuwait (2010-2022): A National Time-Series Analysis.

Journal of clinical medicine·2026
Same author

FTIR spectroscopy of peripheral blood mononuclear cells and machine learning: Spectral biomarkers for bacteremia, focal bacterial, and viral infections.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Rapid Diagnosis of Bacteremia in Febrile Pediatric Oncology Patients via Host-Response Infrared Spectroscopy of Blood and Machine Learning.

Analytical chemistry·2026
Same author

Optimizing imbalanced learning with genetic algorithm.

Scientific reports·2025
Same author

Raman spectroscopy in tandem with machine learning - based decision logic methods for characterization and detection of primary precancerous and cancerous cells.

The Analyst·2025

Related Experiment Video

Updated: May 29, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Learning speaker-specific characteristics with a deep neural architecture.

Ke Chen1, Ahmad Salman

  • 1School of Computer Science, University of Manchester, Manchester M13 9PL, UK. chen@cs.manchester.ac.uk

IEEE Transactions on Neural Networks
|September 29, 2011
PubMed
Summary

This study introduces a novel deep neural architecture (DNA) to extract speaker-specific characteristics from speech, improving speaker recognition performance. The approach creates robust, language-independent speaker representations for better verification and segmentation.

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: May 29, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Signal Processing

Background:

  • Speech signals contain mixed linguistic and speaker-specific information.
  • Current acoustic representations often fail to isolate speaker characteristics, limiting speaker recognition (SR) system performance.

Purpose of the Study:

  • To propose a novel deep neural architecture (DNA) for learning speaker-specific characteristics.
  • To develop an overcomplete representation robust to text and language variations.

Main Methods:

  • Utilized mel-frequency cepstral coefficients (MFCCs) as acoustic features.
  • Designed an objective function with contrastive and reconstruction losses.
  • Employed a hybrid learning strategy: unsupervised pretraining followed by supervised fine-tuning.

Main Results:

  • The proposed DNA generated a speaker-specific overcomplete representation.
  • This representation demonstrated robustness across various speakers and languages.
  • The approach showed high insensitivity to the text spoken.

Conclusions:

  • The novel DNA effectively extracts speaker-specific information, outperforming existing methods.
  • The speaker-specific representation is valuable for speaker verification and segmentation tasks.
  • The method offers a promising direction for language-independent speaker recognition.