This is the companion website for the Saxophone Transcription Pipeline - published with the paper “Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline” (under review).

The dataset release contains 50 transcriptions from the Charlie Parker Omnibook.

The released version will contain Music XML scores, performance aligned MIDI and audio for the source separated saxophone stems. Together we hope this dataset will open up new research fields in automatic music transcription (AMT), performance analysis, generative modelling and automatic music scoring to name a few. If you have any questions please get in touch using the details at the bottom of the page.

Thanks for your interest in our work.