Disentangling Score Content And Performance Style For Joint Piano Rendering And Transcription
2025 · Wei Zeng, Junchuan Zhao, Ye Wang
Abstract
Expressive performance rendering (EPR) and automatic piano transcription (APT) are fundamental yet inverse tasks in music information retrieval: EPR generates expressive performances from symbolic scores, while APT recovers scores from performances. Despite their dual nature, prior work has addressed them independently. In this paper we propose a unified framework that jointly models EPR and APT by disentangling note-level score content and global performance style representations from both paired and unpaired data. Our framework is built on a transformer-based sequence-to-sequence architecture and is trained using only sequence-aligned data, without requiring fine-grained note-level alignment. To automate the rendering process while ensuring stylistic compatibility with the score, we introduce an independent diffusion-based performance style recommendation module that generates style embeddings directly from score content. This modular component supports both style transfer and flexib
Authors
(none)
Tags
Stats
Related papers
- End-to-end Real-world Polyphonic Piano Audio-to-score Transcription With Hierarchical Decoding (2024)0.00
- Dexter: Learning And Controlling Performance Expression With Diffusion Models (2024)7.16
- Expressivity-aware Music Performance Retrieval Using Mid-level Perceptual Features And Emotion Word Embeddings (2024)0.00
- Audio-to-score Alignment Of Piano Music Using Rnn-based Automatic Music Transcription (2017)0.00
- A Convolutional-attentional Neural Framework For Structure-aware Performance-score Synchronization (2022)6.34
- Play As You Like: Timbre-enhanced Multi-modal Music Style Transfer (2018)9.92
- Unified Cross-modal Translation Of Score Images, Symbolic Music, And Performance Audio (2025)0.00
- Piano Transcription By Hierarchical Language Modeling With Pretrained Roll-based Encoders (2025)4.52