A New Auditory Multi-Class Brain-Computer Interface Paradigm: Spatial Hearing as an Informative Cue

Abstract

Most P300-based brain-computer interface (BCI) approaches use the visual modality for stimulation. For use with patients suffering from amyotrophic lateral sclerosis (ALS) this might not be the preferable choice because of sight deterioration. Moreover, using a modality different from the visual one minimizes interference with possible visual feedback. Therefore, a multi-class BCI paradigm is proposed that uses spatially distributed, auditory cues. Ten healthy subjects participated in an offline oddball task with the spatial location of the stimuli being a discriminating cue. Experiments were done in free field, with an individual speaker for each location. Different inter-stimulus intervals of 1000 ms, 300 ms and 175 ms were tested. With averaging over multiple repetitions, selection scores went over 90% for most conditions, i.e., in over 90% of the trials the correct location was selected. One subject reached a 100% correct score. Corresponding information transfer rates were high, up to an average score of 17.39 bits/minute for the 175 ms condition (best subject 25.20 bits/minute). When presenting the stimuli through a single speaker, thus effectively canceling the spatial properties of the cue, selection scores went down below 70% for most subjects. We conclude that the proposed spatial auditory paradigm is successful for healthy subjects and shows promising results that may lead to a fast BCI that solely relies on the auditory sense.

A low-cost auditory multi-class brain-computer interface based on pitch, spatial and timbre cues

“…When looking at the occipital channels though (figures 10, 11, 12), we can see an early positive deflection about 220 ms after the target stimuli presentation. This aligns with the results of Schreuder et al [7], where it is concluded that in the short 175 ms condition "class difference has shifted toward the frontal areas when compared to the longer 1000 ms ISI condition". Despite using a low-cost EEG device, the performance of the proposed system is comparable to state-of-the-art performance.…”

“…This resulted to the conclusion that bigger ISIs give better selection accuracy. The opposite results were obtained by Schreuder et al [7], when a separate classifier was trained for each condition.…”

“…In a more related study [7], a multi class BCI experiment, which used spatially distributed, auditory cues was conducted. The stimulus set consisted of 8 stimuli, different in pitch.…”

“…However, most of the existing P300-based BCI systems rely on visual stimulation, which may not be suitable for patients with sight deterioration, such as patients suffering from Amyotrophic Lateral Sclerosis (ALS). In the case of patients who are unable to direct their gaze, adjust their focus or blink, an auditory P300-based interface might be a better alternative [2][3][4][5][6][7][8][9]. Furthermore, the use of auditory P300-based interfaces for patients with residual vision could allow visual stimuli to be used only as a feedback channel, therefore preventing interaction stimulation and feedback.…”

Brain-Computer Interfaces in Medicine

“…Steady-state visual evoked potentials have been used for binary selection, [48][49][50][51] both discrete and continuous control of a cursor in 2 dimensions, 52 prosthesis control, 53 FES, 54,55 spelling, 56 and environmental control. 57 For patients with impaired vision, various auditory 39,40,[58][59][60][61] and tactile [62][63][64][65] paradigms have been investigated. A few studies are now focused on the critical need to move BCI systems out of the laboratory and into patients' homes, which raises many complex patient, caregiver, and implementation issues.…”