FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914688723320832 |
|---|---|
| author | von Rütte, Dimitri Biggio, Luca Kilcher, Yannic Hofmann, Thomas |
| author_facet | von Rütte, Dimitri Biggio, Luca Kilcher, Yannic Hofmann, Thomas |
| contents | Generating music with deep neural networks has been an area of active research in recent years. While the quality of generated samples has been steadily increasing, most methods are only able to exert minimal control over the generated sequence, if any. We propose the self-supervised description-to-sequence task, which allows for fine-grained controllable generation on a global level. We do so by extracting high-level features about the target sequence and learning the conditional distribution of sequences given the corresponding high-level description in a sequence-to-sequence modelling setup. We train FIGARO (FIne-grained music Generation via Attention-based, RObust control) by applying description-to-sequence modelling to symbolic music. By combining learned high level features with domain knowledge, which acts as a strong inductive bias, the model achieves state-of-the-art results in controllable symbolic music generation and generalizes well beyond the training distribution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2201_10936 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control von Rütte, Dimitri Biggio, Luca Kilcher, Yannic Hofmann, Thomas Sound Machine Learning Audio and Speech Processing Generating music with deep neural networks has been an area of active research in recent years. While the quality of generated samples has been steadily increasing, most methods are only able to exert minimal control over the generated sequence, if any. We propose the self-supervised description-to-sequence task, which allows for fine-grained controllable generation on a global level. We do so by extracting high-level features about the target sequence and learning the conditional distribution of sequences given the corresponding high-level description in a sequence-to-sequence modelling setup. We train FIGARO (FIne-grained music Generation via Attention-based, RObust control) by applying description-to-sequence modelling to symbolic music. By combining learned high level features with domain knowledge, which acts as a strong inductive bias, the model achieves state-of-the-art results in controllable symbolic music generation and generalizes well beyond the training distribution. |
| title | FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control |
| topic | Sound Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2201.10936 |