pith. sign in
Pith Number

pith:UO73INGQ

pith:2026:UO73INGQ6QVP4N3BGDG4FOK5ZN
not attested not anchored not stored refs resolved

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

Chihiro Nagashima, Christian Simon, Junghyun Koo, Keisuke Toyama, Kin Wai Cheuk, Qiyu Wu, Shusuke Takahashi, Shuyang Cui, Woosung Choi, Yukara Ikemiya, Zachary Novack, Zhi Zhong

A fine-tuned text-to-audio model converts high-resolution drum MIDI into matching audio while adopting a reference timbre.

arxiv:2605.14555 v1 · 2026-05-14 · cs.SD · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{UO73INGQ6QVP4N3BGDG4FOK5ZN}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

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.

C2weakest assumption

The proposed content encoder and hybrid conditioning mechanism, when applied via fine-tuning to a pre-trained text-to-audio model, can effectively handle polyphonic percussive drum synthesis using the constructed paired dataset.

C3one line summary

Break-the-Beat! renders drum MIDI audio that matches the timbre of a reference clip by fine-tuning a text-to-audio model with a content encoder and hybrid conditioning on a new paired dataset.

References

45 extracted · 45 resolved · 4 Pith anchors

[1] INTRODUCTION In digital music production, drums play a foundational role in shap- ing the rhythm, energy, and overall character of a composition. Con- ventional workflows for creating expressive drum
[2] Break-the-Beat! Controllable MIDI-to-Drum Audio Synthesis 2026 · arXiv:2605.14555
[3] 1 shows the overview of our proposed method
[4] EXPERIMENTS 4.1. Data We train and evaluate our approach on two variations of the Groove MIDI Dataset (GMD)[30], which consists of 1059 unique human- performed MIDI drum sequences aligned with corresp 2048
[5] RESULTS our model’s key capabilities are evaluated in this section. 5.1. Temporal Granularity We train our proposed method with drum MIDI representations of different temporal resolutions. As expected

Cited by

1 paper in Pith

Receipt and verification
First computed 2026-05-17T23:39:05.660221Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

a3bfb434d0f42afe376130cdc2b95dcb7c0417744ee0692333cafd67c58abf4a

Aliases

arxiv: 2605.14555 · arxiv_version: 2605.14555v1 · doi: 10.48550/arxiv.2605.14555 · pith_short_12: UO73INGQ6QVP · pith_short_16: UO73INGQ6QVP4N3B · pith_short_8: UO73INGQ
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/UO73INGQ6QVP4N3BGDG4FOK5ZN \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: a3bfb434d0f42afe376130cdc2b95dcb7c0417744ee0692333cafd67c58abf4a
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "c5b6af7c1e2e913891b823f93fe02a12fd9f75f8ffdb199fd73e047911a3b25b",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.SD",
    "submitted_at": "2026-05-14T08:32:38Z",
    "title_canon_sha256": "34559a8ef50d7b4b65f582cbe5171bad4cfcd0ff0d23d87aa4c972511a72f939"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14555",
    "kind": "arxiv",
    "version": 1
  }
}