GAN-based Content-Conditioned Generation of Handwritten Musical Symbols
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911222562029568 |
|---|---|
| author | Asbert, Gerard Torras, Pau Kang, Lei Fornés, Alicia Lladós, Josep |
| author_facet | Asbert, Gerard Torras, Pau Kang, Lei Fornés, Alicia Lladós, Josep |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17869 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GAN-based Content-Conditioned Generation of Handwritten Musical Symbols Asbert, Gerard Torras, Pau Kang, Lei Fornés, Alicia Lladós, Josep Computer Vision and Pattern Recognition I.2.6; I.4.9; J.5 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. |
| title | GAN-based Content-Conditioned Generation of Handwritten Musical Symbols |
| topic | Computer Vision and Pattern Recognition I.2.6; I.4.9; J.5 |
| url | https://arxiv.org/abs/2510.17869 |