Fully Automatic Page Turning on Real Scores

TL;DR

This paper introduces a fully automatic page turning system for sheet music that uses a multi-modal neural network to analyze sheet images and live performances, enabling seamless, real-time page turning without symbolic music representations.

Contribution

The novel system combines visual sheet music analysis with audio input to automatically predict page turns, demonstrated through a prototype that physically turns pages in real time.

Findings

Effective real-time page prediction from sheet images and audio

Successful integration with a physical page-turning device

Potential for hands-free music performance support

Abstract

We present a prototype of an automatic page turning system that works directly on real scores, i.e., sheet images, without any symbolic representation. Our system is based on a multi-modal neural network architecture that observes a complete sheet image page as input, listens to an incoming musical performance, and predicts the corresponding position in the image. Using the position estimation of our system, we use a simple heuristic to trigger a page turning event once a certain location within the sheet image is reached. As a proof of concept we further combine our system with an actual machine that will physically turn the page on command.