An audio file is transformed into a Gabor spectrogram. This is used to compare the audio file to a database of audio files, each represented as a Gabor spectrogram. Before two spectrograms are compared, they are aligned. The spectrograms are broken into blocks and individual Gabor vectors in the blocks are compared. Similarities are stored and an aggregate similarity value is derived for the block. After a series of such comparisons and shifting of the secondary spectrogram block, essentially a running window, an offset value is determined. This offset is used to align the two spectrograms at which stage the spectrograms can be compared in a more effective and meaningful manner. A set of observables is derived from the comparisons and the primary spectrogram is classified in way suitable for the application environment.