# DARC: Drum accompaniment generation with fine-grained rhythm control

arXiv: https://arxiv.org/abs/2601.02357 · HTML: https://mlsanity.com/paper/2601.02357/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 5 Jan 2026.

## Builds on (most cited first, 25 of 25)

- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [FMA: A Dataset For Music Analysis](https://mlsanity.com/paper/1612.01840/) (2016)
- [DDSP: Differentiable Digital Signal Processing](https://mlsanity.com/paper/2001.04643/) (2020)
- [Hybrid Transformers for Music Source Separation](https://mlsanity.com/paper/2211.08553/) (2022)
- [Hybrid Spectrogram and Waveform Source Separation](https://mlsanity.com/paper/2111.03600/) (2021)
- [Music ControlNet: Multiple Time-varying Controls for Music Generation](https://mlsanity.com/paper/2311.07069/) (2023)
- [SingSong: Generating musical accompaniments from singing](https://mlsanity.com/paper/2301.12662/) (2023)
- [Moisesdb: A dataset for source separation beyond 4-stems](https://mlsanity.com/paper/2307.15913/) (2023)
- [Learning to Groove with Inverse Sequence Transformations](https://mlsanity.com/paper/1905.06118/) (2019)
- [StemGen: A music generation model that listens](https://mlsanity.com/paper/2312.08723/) (2023)
- [Beat this! Accurate beat tracking without DBN postprocessing](https://mlsanity.com/paper/2407.21658/) (2024)
- [Content-based Controls For Music Large Language Modeling](https://mlsanity.com/paper/2310.17162/) (2023)
- [COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations](https://mlsanity.com/paper/2404.16969/) (2024)
- [High Fidelity Text-Guided Music Editing via Single-Stage Flow Matching](https://mlsanity.com/paper/2407.03648/) (2024)
- [MusicGen-Stem: Multi-stem music generation and edition through autoregressive modeling](https://mlsanity.com/paper/2501.01757/) (2025)
- [JukeDrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAE](https://mlsanity.com/paper/2210.06007/) (2022)
- [MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation](https://mlsanity.com/paper/2407.15060/) (2024)
- [Combining audio control and style transfer using latent diffusion](https://mlsanity.com/paper/2408.00196/) (2024)
- [Latent Diffusion Bridges for Unsupervised Musical Audio Timbre Transfer](https://mlsanity.com/paper/2409.06096/) (2024)
- [STAGE: Stemmed Accompaniment Generation through Prefix-Based Conditioning](https://mlsanity.com/paper/2504.05690/) (2025)
- [The Rhythm In Anything: Audio-Prompted Drums Generation with Masked Language Modeling](https://mlsanity.com/paper/2509.15625/) (2025)
- [A New Dataset for Amateur Vocal Percussion Analysis](https://mlsanity.com/paper/2009.11737/) (2020)
- [Generating Coherent Drum Accompaniment With Fills And Improvisations](https://mlsanity.com/paper/2209.00291/) (2022)
- [Subtractive Training for Music Stem Insertion using Latent Diffusion Models](https://mlsanity.com/paper/2406.19328/) (2024)
- [An Ensemble Approach to Music Source Separation: A Comparative Analysis of Conventional and Hierarchical Stem Separation](https://mlsanity.com/paper/2410.20773/) (2024)

## Built on by (most cited first, 2 of 2)

- [Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs](https://mlsanity.com/paper/2605.10281/) (2026)
- [Seconds-Aligned PCA-DAC Latent Diffusion for Symbolic-to-Audio Drum Rendering](https://mlsanity.com/paper/2605.13404/) (2026)

## Abstract (arXiv)

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.