Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Cortical activation during auditory working memory varies with hearing aid use status in age-related hearing loss.

Scientific reports·2026

Same author

Outliers (typically) cannot cause type I errors in one-sample/paired t-tests.

PloS one·2026

Same author

Perceptual Learning and Predictability of Children's Speech.

Journal of speech, language, and hearing research : JSLHR·2025

Same author

Toward Unified Biomarkers for Focal Epilepsy.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2025

Same author

Does the Spatiotemporal Index (STI) Overestimate Instability in Slow Speech? Investigating Template Effects on the STI Across Different Speaking Rates.

Journal of speech, language, and hearing research : JSLHR·2025

Same author

Centromedian nucleus targeting in the pediatric population treated with thalamic responsive neurostimulation for drug-resistant epilepsy.

Epilepsia open·2025

Same journal

A Multi-Head Attention Transformer Model for Wearable in Situ Fall Detection.

IEEE access : practical innovations, open solutions·2026

Same journal

Validating Single-Camera Pose Estimation Against Multi-Camera Motion Capture for Accessible Biomechanical Assessment.

IEEE access : practical innovations, open solutions·2026

Same journal

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification.

IEEE access : practical innovations, open solutions·2026

Same journal

Radio-Frequency Toroid Susceptometry of Magnetic Nanoparticles: What Goes Around Comes Around.

IEEE access : practical innovations, open solutions·2026

Same journal

Cross-Architecture Knowledge Distillation for Histopathological Image Analysis.

IEEE access : practical innovations, open solutions·2026

Same journal

Mislabel Identification Using Transfer Learning-Based Ensemble Method.

IEEE access : practical innovations, open solutions·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 29, 2025

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

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

Published on: July 26, 2013

MEG Sensor Selection for Neural Speech Decoding.

Debadatta Dash^1,2, Alan Wisler³, Paul Ferrari^4,5

¹Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX 78712, USA.

IEEE Access : Practical Innovations, Open Solutions

|November 18, 2020

Summary

This summary is machine-generated.

Researchers identified an optimal set of nine Magnetoencephalography (MEG) sensors for brain-computer interfaces (BCI). This minimal sensor configuration achieved high accuracy in decoding speech, paving the way for practical, wearable BCI devices.

Keywords:

Autoencoder OPM SVM brain-computer interface forward selection algorithm magnetoencephalography neural speech decoding

More Related Videos

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

Related Experiment Videos

Last Updated: Nov 29, 2025

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

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

Published on: July 26, 2013

Decoding Natural Behavior from Neuroethological Embedding

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

Area of Science:

Neuroscience
Biomedical Engineering
Signal Processing

Background:

Direct speech decoding via brain-computer interfaces (BCI) offers a faster alternative to electroencephalography (EEG) spellers for communication-impaired individuals.
Magnetoencephalography (MEG) shows promise for non-invasive neural speech decoding due to its high temporal resolution and spatial selectivity.
Conventional MEG systems are bulky and require cryogens, limiting their use in wearable BCI applications.

Purpose of the Study:

To identify an optimal, reduced set of MEG channels for decoding imagined and spoken speech.
To evaluate the feasibility of using fewer sensors for practical, wearable MEG-based BCI systems.
To investigate the contribution of different brain regions to speech decoding using MEG.

Main Methods:

Utilized a forward selection algorithm coupled with a support vector machine classifier to determine optimal sensor placement.
Compared decoding accuracy using a minimal set of sensors against using all available channels.
Employed dimensionality reduction techniques, including stacked sparse autoencoders, for comparison.

Main Results:

An optimal set of nine strategically located MEG gradiometers yielded higher speech decoding accuracy than using all sensors.
The forward selection algorithm demonstrated performance comparable to dimensionality reduction methods.
Analysis indicated that speech decoding involves contributions from sensors in both left and right hemispheres, particularly near Broca's area.

Conclusions:

A minimal, optimized set of MEG sensors can effectively decode speech, enhancing the practicality of MEG-based BCIs.
Optically Pumped Magnetometers (OPMs) offer a path towards wearable and modular MEG systems for BCI.
Future BCI development should focus on sensor optimization to reduce size, weight, and cost while maintaining high performance.