STRUM: A Spectral Transcription and Rhythm Understanding Model for End-to-End Generation of Playable Rhythm-Game Charts
This work provides a complete, open-source pipeline for generating playable charts from arbitrary audio, addressing a practical need for rhythm-game enthusiasts and content creators.
STRUM converts raw audio recordings into playable rhythm-game charts for drums, guitar, bass, vocals, and keys without oracle metadata, achieving drum onset F1=0.838, bass F1=0.694, guitar F1=0.651, and vocals F1=0.539 on a 30-song benchmark.
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.