DARC: Drum accompaniment generation with fine-grained rhythm control

Read full text
Authors: Trey Brosnan
Cited by: 0

Abstract

In music creation, rapid prototyping is essential for exploring and refining ideas, yet existing generative tools often fall short when users require both structural control and stylistic flexibility. Prior approaches in stem-to-stem generation can condition on other musical stems but offer limited control over rhythm, and timbre-transfer methods allow users to specify specific rhythms, but cannot condition on musical context. We introduce DARC, a generative drum accompaniment model that conditions both on musical context from other stems and explicit rhythm prompts such as beatboxing or tapping tracks. Using parameter-efficient fine-tuning, we augment STAGE, a state-of-the-art drum stem generator, with fine-grained rhythm control while maintaining musical context awareness.

Fields of Study & Subjects

Music Technology and Sound Studies Music and Audio Processing Interactive and Immersive Displays

Publication details

Journal / source
arXiv (Cornell University)
Publication date
5 January 2026
Document type
Preprint