Related Experiment Video
Updated: Dec 16, 2025
08:45
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
Published on: October 24, 2012
15.0K
Decoding the Attended Speaker From EEG Using Adaptive Evaluation Intervals Captures Fluctuations in Attentional
Manuela Jaeger1,2, Bojana Mirkovic1,3, Martin G Bleichner1,4
1Neuropsychology Lab, Department of Psychology, University of Oldenburg, Oldenburg, Germany.
Frontiers in Neuroscience
|July 3, 2020
Summary
This study introduces an online auditory attention decoding (AAD) pipeline using electroencephalogram (EEG) to track focus on speech in noise. Results show online AAD is feasible and can objectively measure listening effort and performance.
Area of Science:
- Neuroscience
- Cognitive Science
- Auditory Perception
Background:
- Individual differences in speech intelligibility in noise suggest cognitive factors beyond hearing ability.
- Understanding temporal dynamics of selective auditory attention is crucial for explaining these differences.
Purpose of the Study:
- To develop and validate an online auditory attention decoding (AAD) processing pipeline using electroencephalogram (EEG).
- To investigate the temporal dynamics of selective auditory attention in a complex listening environment.
- To link online AAD performance to behavioral outcomes and subjective listener experiences.
Main Methods:
- Developed an online AAD pipeline based on speech envelope tracking in EEG.
- Participants listened to one audiobook while ignoring another.
- Combined an established AAD method with an adaptive staircase procedure to compute individual temporal attention profiles.
Main Results:
- The online AAD pipeline demonstrated feasible decoding of attended speech above chance level.
- Individual decoding performance over time correlated significantly with behavioral performance in the selective listening task.
- Exploratory analysis revealed poor decoding performance was associated with higher reported listening effort and fatigue.
Conclusions:
- Online EEG-based AAD is a feasible method for complex auditory attention tasks.
- Adaptive attended speaker decoding profiles offer an objective measure of behavioral performance and listening effort.
- The developed pipeline can support future near real-time auditory neurofeedback systems.
