MusicAOG: an Energy-Based Model for Learning and Sampling a Hierarchical Representation of Symbolic Music
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916081433575424 |
|---|---|
| author | Qian, Yikai Wang, Tianle Tong, Xinyi Jin, Xin Xu, Duo Zheng, Bo Ge, Tiezheng Yu, Feng Zhu, Song-Chun |
| author_facet | Qian, Yikai Wang, Tianle Tong, Xinyi Jin, Xin Xu, Duo Zheng, Bo Ge, Tiezheng Yu, Feng Zhu, Song-Chun |
| contents | In addressing the challenge of interpretability and generalizability of artificial music intelligence, this paper introduces a novel symbolic representation that amalgamates both explicit and implicit musical information across diverse traditions and granularities. Utilizing a hierarchical and-or graph representation, the model employs nodes and edges to encapsulate a broad spectrum of musical elements, including structures, textures, rhythms, and harmonies. This hierarchical approach expands the representability across various scales of music. This representation serves as the foundation for an energy-based model, uniquely tailored to learn musical concepts through a flexible algorithm framework relying on the minimax entropy principle. Utilizing an adapted Metropolis-Hastings sampling technique, the model enables fine-grained control over music generation. A comprehensive empirical evaluation, contrasting this novel approach with existing methodologies, manifests considerable advancements in interpretability and controllability. This study marks a substantial contribution to the fields of music analysis, composition, and computational musicology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_02678 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MusicAOG: an Energy-Based Model for Learning and Sampling a Hierarchical Representation of Symbolic Music Qian, Yikai Wang, Tianle Tong, Xinyi Jin, Xin Xu, Duo Zheng, Bo Ge, Tiezheng Yu, Feng Zhu, Song-Chun Sound Multimedia Audio and Speech Processing In addressing the challenge of interpretability and generalizability of artificial music intelligence, this paper introduces a novel symbolic representation that amalgamates both explicit and implicit musical information across diverse traditions and granularities. Utilizing a hierarchical and-or graph representation, the model employs nodes and edges to encapsulate a broad spectrum of musical elements, including structures, textures, rhythms, and harmonies. This hierarchical approach expands the representability across various scales of music. This representation serves as the foundation for an energy-based model, uniquely tailored to learn musical concepts through a flexible algorithm framework relying on the minimax entropy principle. Utilizing an adapted Metropolis-Hastings sampling technique, the model enables fine-grained control over music generation. A comprehensive empirical evaluation, contrasting this novel approach with existing methodologies, manifests considerable advancements in interpretability and controllability. This study marks a substantial contribution to the fields of music analysis, composition, and computational musicology. |
| title | MusicAOG: an Energy-Based Model for Learning and Sampling a Hierarchical Representation of Symbolic Music |
| topic | Sound Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2401.02678 |