Music Sheet Understanding and Tone Transposition

Abstract

Optical Music Recognition (OMR) is a sub-field in Artificial Intelligence. Automation of the translation, or understanding music sheets are the main goals of OMR. The application of this field includes the documentation of music sheets for storage or transcribing the music sheet to machine-readable formats [1]. However, on the more applied aspect of OMR, there lacks a practical application for musical Tone Transposition.Tone Transposition is the process of moving a collection of notes up or down in pitch by a constant interval. Traditionally this was a labor-intensive manual process, often impossible during a live performance. Our work proposes a method in which musicians can perform tone transposition by scanning a music sheet, inputting the number of shift tones or semitones required. Finally, the algorithm will output an audio file or a new music sheet with all notes shifted to the required pitch.