Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Shuyang, Zhong, Zhi, Wu, Qiyu, Novack, Zachary, Choi, Woosung, Toyama, Keisuke, Cheuk, Kin Wai, Koo, Junghyun, Ikemiya, Yukara, Simon, Christian, Nagashima, Chihiro, Takahashi, Shusuke
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917495472914432
author Cui, Shuyang
Zhong, Zhi
Wu, Qiyu
Novack, Zachary
Choi, Woosung
Toyama, Keisuke
Cheuk, Kin Wai
Koo, Junghyun
Ikemiya, Yukara
Simon, Christian
Nagashima, Chihiro
Takahashi, Shusuke
author_facet Cui, Shuyang
Zhong, Zhi
Wu, Qiyu
Novack, Zachary
Choi, Woosung
Toyama, Keisuke
Cheuk, Kin Wai
Koo, Junghyun
Ikemiya, Yukara
Simon, Christian
Nagashima, Chihiro
Takahashi, Shusuke
contents Current methods for creating drum loop audio in digital music production, such as using one-shot samples or resampling, often demand non-trivial efforts of creators. While recent generative models achieve high fidelity and adhere to text, they lack the specific control needed for such a task. Existing symbolic-to-audio research often focuses on single, tonal instruments, leaving the challenge of polyphonic, percussive drum synthesis unaddressed. We address this gap by introducing ``Break-the-Beat!,'' a model capable of rendering a drum MIDI with the timbre of a reference audio. It is built by fine-tuning a pre-trained text-to-audio model with our proposed content encoder and a effective hybrid conditioning mechanism. To enable this, we construct a new dataset of paired target-reference drum audio from existing drum audio datasets. Experiments demonstrate that our model generates high-quality drum audio that follows high-resolution drum MIDI, achieving strong performance across metrics of audio quality, rhythmic alignment, and beat continuity. This offer producers a new, controllable tool for creative production. Demo page: https://ik4sumii.github.io/break-the-beat/
format Preprint
id arxiv_https___arxiv_org_abs_2605_14555
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis
Cui, Shuyang
Zhong, Zhi
Wu, Qiyu
Novack, Zachary
Choi, Woosung
Toyama, Keisuke
Cheuk, Kin Wai
Koo, Junghyun
Ikemiya, Yukara
Simon, Christian
Nagashima, Chihiro
Takahashi, Shusuke
Sound
Artificial Intelligence
Current methods for creating drum loop audio in digital music production, such as using one-shot samples or resampling, often demand non-trivial efforts of creators. While recent generative models achieve high fidelity and adhere to text, they lack the specific control needed for such a task. Existing symbolic-to-audio research often focuses on single, tonal instruments, leaving the challenge of polyphonic, percussive drum synthesis unaddressed. We address this gap by introducing ``Break-the-Beat!,'' a model capable of rendering a drum MIDI with the timbre of a reference audio. It is built by fine-tuning a pre-trained text-to-audio model with our proposed content encoder and a effective hybrid conditioning mechanism. To enable this, we construct a new dataset of paired target-reference drum audio from existing drum audio datasets. Experiments demonstrate that our model generates high-quality drum audio that follows high-resolution drum MIDI, achieving strong performance across metrics of audio quality, rhythmic alignment, and beat continuity. This offer producers a new, controllable tool for creative production. Demo page: https://ik4sumii.github.io/break-the-beat/
title Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2605.14555