Low-Data Classification of Historical Music Manuscripts: A Few-Shot Learning Approach
This addresses the challenge of preserving cultural heritage through digital archiving for music historians and archivists, though it is incremental in applying existing few-shot learning methods to a specific domain.
The paper tackles the problem of classifying musical symbols in historical manuscripts with limited labeled data by developing a self-supervised learning framework, achieving an accuracy of 87.66%.
In this paper, we explore the intersection of technology and cultural preservation by developing a self-supervised learning framework for the classification of musical symbols in historical manuscripts. Optical Music Recognition (OMR) plays a vital role in digitising and preserving musical heritage, but historical documents often lack the labelled data required by traditional methods. We overcome this challenge by training a neural-based feature extractor on unlabelled data, enabling effective classification with minimal samples. Key contributions include optimising crop preprocessing for a self-supervised Convolutional Neural Network and evaluating classification methods, including SVM, multilayer perceptrons, and prototypical networks. Our experiments yield an accuracy of 87.66\%, showcasing the potential of AI-driven methods to ensure the survival of historical music for future generations through advanced digital archiving techniques.