{"ID":2893944,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.12175","arxiv_id":"2507.12175","title":"RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection","abstract":"This study introduces RUMAA, a transformer-based framework for music performance analysis that unifies score-to-performance alignment, score-informed transcription, and mistake detection in a near end-to-end manner. Unlike prior methods addressing these tasks separately, RUMAA integrates them using pre-trained score and audio encoders and a novel tri-stream decoder capturing task interdependencies through proxy tasks. It aligns human-readable MusicXML scores with repeat symbols to full-length performance audio, overcoming traditional MIDI-based methods that rely on manually unfolded score-MIDI data with pre-specified repeat structures. RUMAA matches state-of-the-art alignment methods on non-repeated scores and outperforms them on scores with repeats in a public piano music dataset, while also delivering promising transcription and mistake detection results.","short_abstract":"This study introduces RUMAA, a transformer-based framework for music performance analysis that unifies score-to-performance alignment, score-informed transcription, and mistake detection in a near end-to-end manner. Unlike prior methods addressing these tasks separately, RUMAA integrates them using pre-trained score an...","url_abs":"https://arxiv.org/abs/2507.12175","url_pdf":"https://arxiv.org/pdf/2507.12175v1","authors":"[\"Sungkyun Chang\",\"Simon Dixon\",\"Emmanouil Benetos\"]","published":"2025-07-16T12:13:13Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.CL\",\"cs.LG\",\"eess.AS\"]","methods":"[\"Transformer\"]","has_code":false}