Selective attention to visual or auditory stimuli that elicits steady-state visual or auditory responses (SSVEP or ASSR respectively) amplifies the power of those flickering frequencies of the stimuli measured in the electroencephalography (EEG). The design of brain-computer interfaces (BCI) based on selective attention to auditory stimuli that elicits ASSRs has two major advantages: First, no much training is needed as selective attention is an inherent skill of human beings. Second, as the human hearing system behaves as an amplitude modulated (AM) envelope detector, if the auditory stimuli are previously AM modulated, a steady-state response signal can be easily elicited. As EEG signals are considered to be non stationary, this is an interesting approach to EEG analysis as the feature of our interest can be considered stationary, hence Fourier analysis applied. In this paper we study the behavior of a perceptron as a classifier of a BCI system where the features for classification are extracted from EEG as responses to AM modulated auditory stimuli and how we can use it in a BCI system.