10.5281/zenodo.3527748
https://zenodo.org/records/3527748
oai:zenodo.org:3527748
Thitaree Tanprasert
Thitaree Tanprasert
Teerapat Jenrungrot
Teerapat Jenrungrot
Meinard Müller
Meinard Müller
Timothy Tsai
Timothy Tsai
MIDI-Sheet Music Alignment Using Bootleg Score Synthesis
ISMIR
2019
2019-11-04
10.5281/zenodo.3527747
https://zenodo.org/communities/ismir
Creative Commons Attribution 4.0 International
MIDI-sheet music alignment is the task of finding correspondences between a MIDI representation of a piece and its corresponding sheet music images. Rather than using optical music recognition to bridge the gap between sheet music and MIDI, we explore an alternative approach: projecting the MIDI data into pixel space and performing alignment in the image domain. Our method converts the MIDI data into a crude representation of the score that only contains rectangular floating notehead blobs, a process we call bootleg score synthesis. Furthermore, we project sheet music images into the same bootleg space by applying a deep watershed notehead detector and filling in the bounding boxes around each detected notehead. Finally, we align the bootleg representations using a simple variant of dynamic time warping. On a dataset of 68 real scanned piano scores from IMSLP and corresponding MIDI performances, our method achieves a 97.3% accuracy at an error tolerance of one second, outperforming several baseline systems that employ optical music recognition.