SDAILGMay 31, 2022

Towards Context-Aware Neural Performance-Score Synchronisation

arXiv:2206.00454v1h-index: 7
Originality Incremental advance
AI Analysis

This work addresses synchronization challenges for applications in music education, performance analysis, and editing, but it is incremental as it builds on existing performance-score synchronization research.

The research tackled the problem of music performance-score synchronization by proposing data-driven, context-aware alignment methods, resulting in approaches that are adaptable to different acoustic settings, handle structural differences, and perform well in data-scarce conditions.

Music can be represented in multiple forms, such as in the audio form as a recording of a performance, in the symbolic form as a computer readable score, or in the image form as a scan of the sheet music. Music synchronisation provides a way to navigate among multiple representations of music in a unified manner by generating an accurate mapping between them, lending itself applicable to a myriad of domains like music education, performance analysis, automatic accompaniment and music editing. Traditional synchronisation methods compute alignment using knowledge-driven and stochastic approaches, typically employing handcrafted features. These methods are often unable to generalise well to different instruments, acoustic environments and recording conditions, and normally assume complete structural agreement between the performances and the scores. This PhD furthers the development of performance-score synchronisation research by proposing data-driven, context-aware alignment approaches, on three fronts: Firstly, I replace the handcrafted features by employing a metric learning based approach that is adaptable to different acoustic settings and performs well in data-scarce conditions. Secondly, I address the handling of structural differences between the performances and scores, which is a common limitation of standard alignment methods. Finally, I eschew the reliance on both feature engineering and dynamic programming, and propose a completely data-driven synchronisation method that computes alignments using a neural framework, whilst also being robust to structural differences between the performances and scores.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes