A Convolutional-Attentional Neural Framework for Structure-Aware Performance-Score Synchronization

TL;DR

This paper introduces a novel data-driven, structure-aware neural framework that improves performance-score synchronization across various modalities and acoustic conditions, outperforming traditional methods.

Contribution

The paper presents a convolutional-attentional neural architecture with a custom loss for robust, structure-aware synchronization across multiple score modalities and conditions.

Findings

Outperforms state-of-the-art synchronization methods

Robust to structural differences between performance and score

Effective across different score modalities and acoustic environments

Abstract

Performance-score synchronization is an integral task in signal processing, which entails generating an accurate mapping between an audio recording of a performance and the corresponding musical score. Traditional synchronization methods compute alignment using knowledge-driven and stochastic approaches, and are typically unable to generalize well to different domains and modalities. We present a novel data-driven method for structure-aware performance-score synchronization. We propose a convolutional-attentional architecture trained with a custom loss based on time-series divergence. We conduct experiments for the audio-to-MIDI and audio-to-image alignment tasks pertained to different score modalities. We validate the effectiveness of our method via ablation studies and comparisons with state-of-the-art alignment approaches. We demonstrate that our approach outperforms previous synchronization methods for a variety of test settings across score modalities and acoustic conditions. Our method is also robust to structural differences between the performance and score sequences, which is a common limitation of standard alignment approaches.