Classifying Polyphonic Melodies by Chord Estimation Based on Hidden Markov Model

In this investigation we propose a novel approach for classifying polyphonic melodies. Our main idea comes from for automatic classi cation of polyphonic melodies by Hidden Markov model where the states correspond to well-tempered chords over the music and the observation sequences to some feature values called pitch spectrum. The similarity among harmonies can be considered by means of the features and well-tempered chords. We show the e ectiveness and the usefulness of the approach by some experimental results.