# GAN-based Content-Conditioned Generation of Handwritten Musical Symbols

arXiv: https://arxiv.org/abs/2510.17869 · HTML: https://mlsanity.com/paper/2510.17869/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 16 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images](https://mlsanity.com/paper/2003.02567/) (2020)
- [Understanding Optical Music Recognition](https://mlsanity.com/paper/1908.03608/) (2019)
- [Content and Style Aware Generation of Text-line Images for Handwriting Recognition](https://mlsanity.com/paper/2204.05539/) (2022)
- [HWD: A Novel Evaluation Score for Styled Handwritten Text Generation](https://mlsanity.com/paper/2310.20316/) (2023)
- [A Unified Representation Framework for the Evaluation of Optical Music Recognition Systems](https://mlsanity.com/paper/2312.12908/) (2023)
- [Synthesising Handwritten Music with GANs: A Comprehensive Evaluation of CycleWGAN, ProGAN, and DCGAN](https://mlsanity.com/paper/2411.16405/) (2024)

## Abstract (arXiv)

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.