A signal detector discriminates between signals manifesting noise and signals manifesting information, both of which appear at an input. A analog-to-digital converter circuit samples the signals and a Fourier filter determines, for each signal sample, energy content of each of a plurality of frequency cells in the sample. A processor then determines the mean energy content and the average variance of energy content in all frequency cells in the signal sample. The mean energy content and average variance of energy content of the signal sample are then compared, and if the comparison indicates an approximate equality, the sample is declared to be noise. The processor further determines a centroid center frequency for the frequency cells in the sample which indicates, if it is on-center, that the sample is likely to be noise. The processor further determines the bandwidth of the Fourier components of the input signal, to determine if it is indicative of noise. The skew of the sample's Fourier components is also determined and if it is nearly zero (indicating the signal is symmetrical in frequency about the center frequency), a noise signal is indicated. The combined indications are then normalized and subjected to a threshold which indicates whether a signal or noise is present.