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

Enhancing few-shot personalized cuffless blood pressure estimation with self-supervised learning.

Physiological measurement·2026

Same author

Multi-channel Electromagnetic Interference Elimination for Shielding-free MRI Using Null Operations.

IEEE transactions on bio-medical engineering·2026

Same author

Improved Simultaneous Multislice EPI Reconstruction for Diffusion MRI using regularized iterative phase error-corrected SENSE.

NeuroImage·2026

Same author

Brain-wide resting-state fMRI network dynamics elicited by activation of single thalamic input.

Nature communications·2025

Same author

The Effect of Temporal Misalignment Between Acoustic and Simulated Electric Signals on the Time Compression Thresholds of Normal-Hearing Listeners.

Trends in hearing·2025

Same author

The effects of within- and across-ear temporal misalignment between acoustic and simulated electric signals on speech-in-noise recognition.

The Journal of the Acoustical Society of America·2025

Same journal

Cortex-anchored sensor-space harmonics for event-related EEG.

Journal of neural engineering·2026

Same journal

Neural mechanisms of mixed speech and grasp representation in sensorimotor cortices.

Journal of neural engineering·2026

Same journal

Developing a binary communication protocol between biological neural networks using virtual white matter.

Journal of neural engineering·2026

Same journal

Spatiotemporally distinctive astrocytic and neuronal responses to repetitive intracortical microstimulation.

Journal of neural engineering·2026

Same journal

A neural mass modelling framework for evaluating EEG source localisation of seizure activity.

Journal of neural engineering·2026

Same journal

Functional and effective connectivity methods from SEEG for characterizing epileptogenic networks in refractory epilepsy: a comprehensive review and future directions.

Journal of neural engineering·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 6, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

EEG-based auditory attention decoding using speech-level-based segmented computational models.

Lei Wang^1,2, Ed X Wu², Fei Chen¹

¹Department of Electrical and Electronic Engineering, Southern University of Science and Technology, Shenzhen, People's Republic of China.

Journal of Neural Engineering

|May 6, 2021

Summary

This summary is machine-generated.

This study introduces a novel segmented approach for auditory attention decoding (AAD) using electroencephalography (EEG). The method effectively decodes speech envelopes from different speech segments, improving AAD performance in complex auditory environments.

Keywords:

EEG RMS-level-based speech segments auditory attention decoding (AAD)machine learning signal-to-mask ratio (SMR)support vector machine (SVM)temporal response function (TRF)

More Related Videos

Recording Brain Activity with Ear-Electroencephalography

Recording Brain Activity with Ear-Electroencephalography

Published on: March 31, 2023

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Published on: July 5, 2015

Related Experiment Videos

Last Updated: Nov 6, 2025

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

Recording Brain Activity with Ear-Electroencephalography

Recording Brain Activity with Ear-Electroencephalography

Published on: March 31, 2023

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Measurement of Neurophysiological Signals of Ignoring and Attending Processes in Attention Control

Published on: July 5, 2015

Area of Science:

Neuroscience
Signal Processing
Biomedical Engineering

Background:

Auditory attention decoding (AAD) using electroencephalography (EEG) is crucial for understanding complex auditory processing.
Cortical speech-envelope tracking via EEG shows promise, but performance can be limited in noisy environments.
Relative root-mean-square (RMS) intensity is a key feature for segmenting speech signals.

Purpose of the Study:

To develop and evaluate a novel segmented AAD approach for improved performance in complex auditory scenes.
To investigate the utility of RMS-level-based speech segmentation for EEG-based auditory attention decoding.
To compare the proposed segmented AAD method against traditional unified decoding approaches.

Main Methods:

Speech was segmented into higher- and lower-RMS-level segments using a -10 dB threshold.
A support vector machine classifier identified speech segments based on EEG signals.
Segmented computational models were developed to reconstruct speech envelopes for each segment.
AAD accuracy was assessed by correlating reconstructed and actual speech envelopes.

Main Results:

EEG signals robustly classified higher- and lower-RMS speech segments with >80% accuracy across various signal-to-mask ratios (SMRs).
The segmented AAD approach demonstrated superior accuracy in reconstructing speech envelopes and detecting attentional focus compared to unified methods.
The proposed method achieved higher information transfer rates (ITRs) and reduced minimum expected switch times.

Conclusions:

EEG signals can effectively classify speech segments based on RMS levels, even in challenging acoustic conditions (6 dB to -6 dB SMR).
Distinct information within RMS-level-based speech segments significantly enhances EEG-based auditory attention decoding.
The segmented decoding model offers a promising computational approach for brain-computer interfaces in complex auditory environments.