Multiple Piano Note Identification Using a Spectral Matching Method with Derived Patterns
[Engineering Reports] The success of polyphonic detection varies depending on the instrument. Different approaches have been proposed. Piano polyphonic detection is particularly difficult. A special approach to detecting piano chords is described. Using a spectral pattern-matching method, chords containing up to four notes have been identified successfully. Chords throughout the complete tonal range (from octave 1 to octave 7) have been tested and identified. Patterns are generated during a training step that uses an acoustical model of a piano.
Click to purchase paper or login as an AES member. If your company or school subscribes to the AES Journal then you can look for this paper in the institutional version of the Online Journal. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $20 for non-members, $5 for AES members and is free for E-Library subscribers.