Auditory Paradigm for a P300 BCI System using Spatial Hearing

The present paper proposes an auditory BCI paradigm for systems based on P300 signals which are generated by auditory stimuli characterized by different sound typologies and locations. A Head Related Transfer Function approach is adopted to virtualize auditory stimuli. When virtualized audio is used, the user has to focus the attention both on the type and location of the stimulus, thus generating P300 signals whose amplitude is higher than that generated without audio virtualization. Classification is performed by Support Vector Machines in which gaussian radial basis functions are used as kernel functions. The system has been validated with 14 users, who were asked to choose one among five common spoken words, previously virtualized and transmitted to stereophonic headphones. Classification results prove that the proposed auditory BCI system performed similarly to common visual BCI P300 systems, representing then an alternative to visual BCI for users with visual impairments.