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

You might also read

Related Articles

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

Sort by
Same author

Mirror aneurysms of the anterior cerebral artery: distinct clinical profile or just another intracranial aneurysm? A systematic review.

British journal of neurosurgery·2026
Same author

The Green Parkinson's Belt: agricultural regions associated with increased Parkinson's disease burden in Mexico.

Frontiers in aging neuroscience·2026
Same author

Venous Sinus Stenting in Idiopathic Intracranial Hypertension: A Systematic Review of an Emerging Intervention with Favorable Outcomes but Unresolved Standardization.

World neurosurgery·2026
Same author

Endovascular treatment for posterior epistaxis: should it still be considered a last-resort option? A literature review.

Frontiers in surgery·2026
Same author

An EEG-EMG-kinematics dataset from wrist pointing tasks for biomarker research in neurorehabilitation.

Scientific data·2026
Same author

Carotid cavernous fistula in Sturge-Weber syndrome: A unique case and literature review of associated vascular malformations.

Journal of cerebrovascular and endovascular neurosurgery·2026

Related Experiment Video

Updated: Sep 15, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.5K

From pronounced to imagined: improving speech decoding with multi-condition EEG data.

Denise Alonso-Vázquez1, Omar Mendoza-Montoya1, Ricardo Caraza2

  • 1Escuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Monterrey, Mexico.

Frontiers in Neuroinformatics
|July 14, 2025
PubMed
Summary

Incorporating overt speech data into electroencephalography (EEG) models improved imagined speech classification accuracy for individuals with motor neuron diseases. This approach enhances brain-computer interfaces for communication before speech loss.

Keywords:
EEG-based classificationEEGNETbrain-computer interfacesimagined speech classificationovert speech

More Related Videos

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.1K

Related Experiment Videos

Last Updated: Sep 15, 2025

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.5K
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K
A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants
11:14

A Novel Experimental and Analytical Approach to the Multimodal Neural Decoding of Intent During Social Interaction in Freely-behaving Human Infants

Published on: October 4, 2015

11.1K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Speech Processing

Background:

  • Electroencephalography (EEG) based imagined speech decoding shows promise for motor neuron disease patients.
  • Current limitations include small datasets and lack of sensory feedback, hindering performance.
  • Investigating the integration of overt (spoken) speech data to enhance imagined speech classification is crucial.

Purpose of the Study:

  • To determine if incorporating EEG data from overt speech can improve imagined speech classification.
  • To compare different training dataset scenarios for optimizing EEG-based speech decoding.
  • To assess the feasibility of using overt speech data for enhancing brain-computer interfaces (BCIs) in neurodegenerative diseases.

Main Methods:

  • Four classification scenarios were systematically compared: intra-subject (imagined speech only, overt speech only, combined) and multi-subject (combined overt speech with target participant's imagined speech).
  • The convolutional neural network EEGNet was implemented for all classification tasks.
  • Twenty-four healthy participants produced and imagined five Spanish words.

Main Results:

  • Combining overt and imagined speech data in the intra-subject scenario improved binary word-pair classification accuracy by 3%-5.17% for four out of ten pairs compared to using imagined speech alone.
  • While highest individual accuracy (95%) was with imagined speech only, combining data increased participants achieving >70% accuracy from 10 to 15.
  • No statistically significant improvements were observed in the intra-subject multi-class scenario when combining overt and imagined speech data.

Conclusions:

  • Incorporating overt speech data can enhance individualized imagined speech decoding models, offering a practical strategy for BCIs.
  • Features like word length, phonological complexity, and usage frequency influence imagined speech discriminability.
  • This approach supports early BCI adoption for individuals with motor neuron diseases, mitigating challenges before significant speech deterioration.