0.6 Results & Conclusion

Results

Here x is the correct string of notes/chords and y is the one created by our implementation
N is length of x
edit_distance gives the number of changes (insertions, substitutions or deletions) needed to go from string x to y

The average accuracy on testing eight different songs was:

• 92% on songs with single melody line
• 86% on songs with single chord line
• 78% on songs with homophonies

Noise resiliency

Conclusion

Our implementation of a piano note and chord recognition system was successful in varying degrees. Depending upon the texture of the song and independent variables in our algorithm, we were able to get an average accuracy of 87.53%.

We applied our knowledge from ELEC 301 to create the onset detection, gain compression, filtering and spectral analysis algorithms independently. We then augmented our implementation with the use of Harmonic Pitch Class Profile (HPCP) that has the added benefit of noise resiliency.

By exploring the topic of automatic music transcription, and implementing our own version of homophony detection, we have created a base from where we can only improve the accuracy and performance of music recognition automation system.