MUSIC estimates the frequency content of a signal or autocorrelation matrix using an eigenspace method. This method assumes that a signal, x(n), consists of p complex exponentials in the presence of Gaussian white noise. Given an M \times M autocorrelation matrix, \mathbf{R}_x, if the eigenvalues are sorted in decreasing order, the eigenvectors corresponding to the p largest eigenvalues (i.e. directions of largest variability) span the signal subspace. The remaining M-p eigenvectors span the orthogonal space, where there is only noise. Note that for M = p + 1, MUSIC is identical to Pisarenko harmonic decomposition. The general idea is to use averaging to improve the performance of the Pisarenko estimator.