PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915054221262848 |
|---|---|
| author | Liang, Xiao Zhao, Zijian Zeng, Weichao He, Yutong He, Fupeng Wang, Yiyi Gao, Chengying |
| author_facet | Liang, Xiao Zhao, Zijian Zeng, Weichao He, Yutong He, Fupeng Wang, Yiyi Gao, Chengying |
| contents | Learning musical structures and composition patterns is necessary for both music generation and understanding, but current methods do not make uniform use of learned features to generate and comprehend music simultaneously. In this paper, we propose PianoBART, a pre-trained model that uses BART for both symbolic piano music generation and understanding. We devise a multi-level object selection strategy for different pre-training tasks of PianoBART, which can prevent information leakage or loss and enhance learning ability. The musical semantics captured in pre-training are fine-tuned for music generation and understanding tasks. Experiments demonstrate that PianoBART efficiently learns musical patterns and achieves outstanding performance in generating high-quality coherent pieces and comprehending music. Our code and supplementary material are available at https://github.com/RS2002/PianoBart. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03361 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training Liang, Xiao Zhao, Zijian Zeng, Weichao He, Yutong He, Fupeng Wang, Yiyi Gao, Chengying Sound Artificial Intelligence Audio and Speech Processing Learning musical structures and composition patterns is necessary for both music generation and understanding, but current methods do not make uniform use of learned features to generate and comprehend music simultaneously. In this paper, we propose PianoBART, a pre-trained model that uses BART for both symbolic piano music generation and understanding. We devise a multi-level object selection strategy for different pre-training tasks of PianoBART, which can prevent information leakage or loss and enhance learning ability. The musical semantics captured in pre-training are fine-tuned for music generation and understanding tasks. Experiments demonstrate that PianoBART efficiently learns musical patterns and achieves outstanding performance in generating high-quality coherent pieces and comprehending music. Our code and supplementary material are available at https://github.com/RS2002/PianoBart. |
| title | PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2407.03361 |