This paper describes a novel approach for detecting the correctness of musical chords played by guitar. The approach is based on pattern matching technique applied on database of chords and their typical mistakes played with multiple guitars. Spectrum of the chord is whitened and a certain region is selected as a feature vector. The cosine distance is calculated between chord to be tested and a reference chord database, chord detection is done based on the minimum distance. The proposed system is evaluated with isolated chords with different noise conditions. The system shows approximately 77% accuracy in scoring the correctness of played chords with a medium sized database.
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.