DARC: Drum accompaniment generation with fine-grained rhythm control
This work addresses the need for better control and flexibility in music creation tools for artists and producers, though it is incremental as it builds on an existing state-of-the-art model.
The paper tackled the problem of limited rhythm control in generative drum accompaniment tools by introducing DARC, a model that conditions on both musical context and explicit rhythm prompts, achieving fine-grained rhythm control while maintaining context awareness.
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.