SYMPLEX: Controllable Symbolic Music Generation using Simplex Diffusion with Vocabulary Priors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916254329077760 |
|---|---|
| author | Jonason, Nicolas Casini, Luca Sturm, Bob L. T. |
| author_facet | Jonason, Nicolas Casini, Luca Sturm, Bob L. T. |
| contents | We present a new approach for fast and controllable generation of symbolic music based on the simplex diffusion, which is essentially a diffusion process operating on probabilities rather than the signal space. This objective has been applied in domains such as natural language processing but here we apply it to generating 4-bar multi-instrument music loops using an orderless representation. We show that our model can be steered with vocabulary priors, which affords a considerable level control over the music generation process, for instance, infilling in time and pitch and choice of instrumentation -- all without task-specific model adaptation or applying extrinsic control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12666 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SYMPLEX: Controllable Symbolic Music Generation using Simplex Diffusion with Vocabulary Priors Jonason, Nicolas Casini, Luca Sturm, Bob L. T. Sound Machine Learning Audio and Speech Processing We present a new approach for fast and controllable generation of symbolic music based on the simplex diffusion, which is essentially a diffusion process operating on probabilities rather than the signal space. This objective has been applied in domains such as natural language processing but here we apply it to generating 4-bar multi-instrument music loops using an orderless representation. We show that our model can be steered with vocabulary priors, which affords a considerable level control over the music generation process, for instance, infilling in time and pitch and choice of instrumentation -- all without task-specific model adaptation or applying extrinsic control. |
| title | SYMPLEX: Controllable Symbolic Music Generation using Simplex Diffusion with Vocabulary Priors |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.12666 |