From another viewpoint, this ML procedure can be understood as a clustering method under a harmonic constraint between Gaussian mixture components where spectral density function is considered as a statistical distribution of micro-energies along frequency axis. As we regard as cluster centroids, the a posteriori probability in equation (6) as a membership degree of each micro-energy and the log-likelihood as a distance function between centroid and a micro-energy, thus the function in equation (3) turns out to be the objective function for fuzzy clustering. We call this concept ``Harmonic Clustering.''

平成16年3月25日