Validation of cost-efficient EEG experimental setup for neural tracking in an auditory attention task

Area of Science:

• Neuroscience
• Biomedical Engineering
• Signal Processing

Background:

• Neural activity phase-locks to speech rhythm, known as neural tracking.
• Auditory attention decoding (AAD) uses electroencephalography (EEG) to identify attended speech in noisy environments.
• Current EEG systems can be costly and complex, limiting accessibility.

Purpose of the Study:

• To develop a cost-efficient neural tracking system for AAD.
• To validate the feasibility of neural tracking and AAD using affordable hardware.
• To assess system performance in a non-soundproofed, practical environment.

Main Methods:

• Developed a neural tracking system using OpenBCI and Arduino.
• Recruited nine participants for an auditory attention decoding task.
• Utilized competing speech signals in an unshielded experimental setting.
• Evaluated both offline and real-time decoder models.

Main Results:

• The offline decoder model achieved an average performance of 90%.
• The real-time decoder model achieved an average performance of 78%.
• Demonstrated successful neural tracking and AAD outside a soundproof environment.

Conclusions:

• The developed system provides a feasible and cost-effective solution for neural tracking and AAD.
• This approach enhances the accessibility of EEG-based auditory attention research.
• Potential applications include clinical assessments and neuro-steered hearing devices.