Michael Yeung

NOISE-TO-NOTES: DIFFUSION-BASED GENERATION AND REFINEMENT FOR AUTOMATIC DRUM TRANSCRIPTION

Automatic drum transcription (ADT) is traditionally formulated as a discriminative task to predict drum events from audio spectrograms. In this work, we redefine ADT as a conditional generative task and introduce Noise-to-Notes (N2N), a framework leveraging diffusion modeling to transform audio-cond…