GAN-based Content-Conditioned Generation of Handwritten Musical Symbols
This addresses data scarcity for researchers and practitioners in OMR, particularly for historical handwritten scores, but is incremental as it builds on existing GAN and synthesis methods.
The study tackled the scarcity of annotated data in Optical Music Recognition by generating realistic handwritten musical symbols using a GAN and assembling them into full scores, concluding that the generated symbols exhibit a high degree of realism.
The field of Optical Music Recognition (OMR) is currently hindered by the scarcity of real annotated data, particularly when dealing with handwritten historical musical scores. In similar fields, such as Handwritten Text Recognition, it was proven that synthetic examples produced with image generation techniques could help to train better-performing recognition architectures. This study explores the generation of realistic, handwritten-looking scores by implementing a music symbol-level Generative Adversarial Network (GAN) and assembling its output into a full score using the Smashcima engraving software. We have systematically evaluated the visual fidelity of these generated samples, concluding that the generated symbols exhibit a high degree of realism, marking significant progress in synthetic score generation.