GraphMuse: A Library for Symbolic Music Graph Processing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917725137272832 |
|---|---|
| author | Karystinaios, Emmanouil Widmer, Gerhard |
| author_facet | Karystinaios, Emmanouil Widmer, Gerhard |
| contents | Graph Neural Networks (GNNs) have recently gained traction in symbolic music tasks, yet a lack of a unified framework impedes progress. Addressing this gap, we present GraphMuse, a graph processing framework and library that facilitates efficient music graph processing and GNN training for symbolic music tasks. Central to our contribution is a new neighbor sampling technique specifically targeted toward meaningful behavior in musical scores. Additionally, GraphMuse integrates hierarchical modeling elements that augment the expressivity and capabilities of graph networks for musical tasks. Experiments with two specific musical prediction tasks -- pitch spelling and cadence detection -- demonstrate significant performance improvement over previous methods. Our hope is that GraphMuse will lead to a boost in, and standardization of, symbolic music processing based on graph representations. The library is available at https://github.com/manoskary/graphmuse |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_12671 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GraphMuse: A Library for Symbolic Music Graph Processing Karystinaios, Emmanouil Widmer, Gerhard Sound Artificial Intelligence Digital Libraries Audio and Speech Processing Graph Neural Networks (GNNs) have recently gained traction in symbolic music tasks, yet a lack of a unified framework impedes progress. Addressing this gap, we present GraphMuse, a graph processing framework and library that facilitates efficient music graph processing and GNN training for symbolic music tasks. Central to our contribution is a new neighbor sampling technique specifically targeted toward meaningful behavior in musical scores. Additionally, GraphMuse integrates hierarchical modeling elements that augment the expressivity and capabilities of graph networks for musical tasks. Experiments with two specific musical prediction tasks -- pitch spelling and cadence detection -- demonstrate significant performance improvement over previous methods. Our hope is that GraphMuse will lead to a boost in, and standardization of, symbolic music processing based on graph representations. The library is available at https://github.com/manoskary/graphmuse |
| title | GraphMuse: A Library for Symbolic Music Graph Processing |
| topic | Sound Artificial Intelligence Digital Libraries Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.12671 |