Signal processing algorithms for attention decoding of brain responses to natural stimuli in brain-computer interfaces.

Brain-computer interfaces (BCI) enable the human brain to interact with machines, opening doors to various high-impact applications. However, most experimental BCI paradigms require the user to concentrate on synthetic and repeated stimuli, inducing fatigue and interfering with natural behavior. This unnatural interaction hampers widespread usage of BCIs in daily-life situations beyond a few niche clinical applications.In this project, we envisage ‘passive’ electroencephalography (EEG)-based BCI applications that track the user’s attention to natural audio-visual stimuli, allowing seamless integration with daily-life activities. However, this shift comes with several fundamental signal processing challenges, such as (1) the low signal-to-noise ratio of neural responses to natural speech or video footage, (2) the strong user-specificity of these responses, and (3) the multi-modal integration of audio-visual stimuli. We will tackle these challenges by designing novel algorithms that are inherently unsupervised (avoiding the need for a dedicated training session for each end-user), and that exploit side information such as knowledge of the stimuli and data from other users.Although we target generic algorithmic tools for EEG-based BCIs with natural stimuli, we envisage specific breakthroughs in the context of (1) neuro-steered hearing devices, (2) educational neuroscience, and (3) objective hearing screening in daily-life environments, which act as the driver applications.

Keywords:passive brain-computer interfaces, attention decoding, electroencephalography

Disciplines:Machine learning and decision making, Signal processing, Audio and speech processing, Biomedical signal processing