A brain-computer interface (BCI) system based on auditory stream segregation

An auditory brain-computer interface (BCI) which detected event-related potential (ERP) elicited by selective attention to one of the tone streams was proposed. Each tone in two kinds of frequency oddball tone sequences with different tone frequency range was presented alternatively to subjects, and they were perceived by subjects as two kinds of segregated streams. Event-related potentials elicited by two kinds of deviant tones were classified by linear discriminant analysis (LDA) to find which streams subjects paid selective attention. By the experiments to six subjects, it was shown that this system could realize binary selection from two kinds of segregated tone streams.