STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Opria, Joshua
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914558504861696
author Opria, Joshua
author_facet Opria, Joshua
contents We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone Hero / YARG charts for drums, guitar, bass, vocals, and keys without any oracle metadata. STRUM is a multi-stage hybrid: a two-stage CRNN onset detector and a six-model ensemble classifier for drums; neural onset detectors with monophonic pitch tracking for guitar and bass; word-aligned ASR for vocals; and spectral keyboard detection for keys. We evaluate on a 30-song in-envelope benchmark constructed by screening candidate songs on a single audio-quality criterion -- the median 1-second drum-stem RMS after htdemucs_6s source separation. On this benchmark STRUM achieves drums onset F1 = 0.838, bass F1 = 0.694, guitar F1 = 0.651, and vocals F1 = 0.539 at a +/- 100 ms tolerance with per-song global offset search. We report a complete ablation of seven drum-pipeline components with paired per-song Wilcoxon tests, an analysis of ground-truth-to-audio timing distributions in community Clone Hero charts, and a per-class confusion matrix for the drum classifier. Code, model weights, and the full benchmark manifest are released.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12135
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
Opria, Joshua
Sound
Machine Learning
Audio and Speech Processing
cs.LG, eess.AS
H.5.5; I.2.7; I.5.4
We present STRUM (Spectral Transcription and Rhythm Understanding Model), an audio-to-chart pipeline that converts raw recordings into playable Clone Hero / YARG charts for drums, guitar, bass, vocals, and keys without any oracle metadata. STRUM is a multi-stage hybrid: a two-stage CRNN onset detector and a six-model ensemble classifier for drums; neural onset detectors with monophonic pitch tracking for guitar and bass; word-aligned ASR for vocals; and spectral keyboard detection for keys. We evaluate on a 30-song in-envelope benchmark constructed by screening candidate songs on a single audio-quality criterion -- the median 1-second drum-stem RMS after htdemucs_6s source separation. On this benchmark STRUM achieves drums onset F1 = 0.838, bass F1 = 0.694, guitar F1 = 0.651, and vocals F1 = 0.539 at a +/- 100 ms tolerance with per-song global offset search. We report a complete ablation of seven drum-pipeline components with paired per-song Wilcoxon tests, an analysis of ground-truth-to-audio timing distributions in community Clone Hero charts, and a per-class confusion matrix for the drum classifier. Code, model weights, and the full benchmark manifest are released.
title STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
topic Sound
Machine Learning
Audio and Speech Processing
cs.LG, eess.AS
H.5.5; I.2.7; I.5.4
url https://arxiv.org/abs/2605.12135