mlsanityData to 14 Oct 2026

RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection

arXiv 2507.12175 ↗First posted 16 Jul 2025cs.SD cs.CL cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 41 references that are in the map. First posted on arXiv 16 Jul 2025.

Builds on

25 of 41 references.

References · 25

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  3. 2014Neural Turing Machinescited by 644
  4. 2018Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Datasetcited by 217
  5. 2023LongNet: Scaling Transformers to 1,000,000,000 Tokenscited by 204
  6. 2021Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphscited by 110
  7. 2021MT3: Multi-Task Multitrack Music Transcriptioncited by 71
  8. 2024Music2Latent: Consistency Autoencoders for Latent Audio Compressioncited by 33
  9. 2021MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modelingcited by 32
  10. 2023Automatic Piano Transcription with Hierarchical Frequency-Time Transformercited by 22
  11. 2024Scoring Time Intervals using Non-Hierarchical Transformer For Automatic Piano Transcriptioncited by 14
  12. 2024YourMT3+: Multi-instrument Music Transcription with Enhanced Transformer Architectures and Cross-dataset Stem Augmentationcited by 13
13 more
  1. 2024CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Modelscited by 12
  2. 2022TorchScale: Transformers at Scalecited by 10
  3. 2025Scaling Self-Supervised Representation Learning for Symbolic Piano Performancecited by 9
  4. 2021Audio-to-Score Alignment Using Deep Automatic Music Transcriptioncited by 7
  5. 2019Cross-Modal Music Retrieval and Applications: An Overview of Key Methodologiescited by 6
  6. 2019Music Performance Analysis: A Surveycited by 5
  7. 2021Structure-Aware Audio-to-Score Alignment using Progressively Dilated Convolutional Neural Networkscited by 5
  8. 2024PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variationscited by 4
  9. 2020Improved Handling of Repeats and Jumps in Audio-Sheet Image Synchronizationcited by 3
  10. 2025Detecting Music Performance Errors with Transformerscited by 3
  11. 2025ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinementcited by 3
  12. 2024TheGlueNote: Learned Representations for Robust and Flexible Note Alignmentcited by 1
  13. 2024How does the teacher rate? Observations from the NeuroPiano datasetcited by 1

Built on by

Not cited yet.