Year: 2025
Type: preprint
Abstract: Automatic Drum Transcription (ADT) remains a challenging task in MIR but recent advances allow accurate transcription of drum kits with up 5 classes - kick, snare, hi-hats, toms and cymbals - via the ADTOF package. In addition, several drum kit \emph{stem} separation models in the open source community support separation for more than 6 stem classes, including distinct crash and ride cymbals. In this work we explore the benefits of combining these tools to improve the realism of drum transcriptions. We describe a simple post-processing step which expands the transcription output from five to seven classes and furthermore, we are able to estimate MIDI velocity values based on the separated stems. Our solution achieves strong performance when assessed against a baseline of 8-class drum transcription and produces realistic MIDI transcriptions suitable for MIR or music production tasks.
Source: arXiv (Cornell University)
Authors: Riley, Xavier, Dixon, Simon
Language: English
Topic: Music and Audio Processing
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415337461
Cites:
Cited by:
Related to: