PianoBART: Symbolic Piano Music Generation and Understanding with Large-Scale Pre-Training
This work addresses the need for unified models in music AI for musicians and researchers, though it is incremental as it adapts existing pre-training methods to a specific domain.
The paper tackles the problem of generating and understanding symbolic piano music by proposing PianoBART, a pre-trained model based on BART, which achieves outstanding performance in producing high-quality coherent pieces and comprehending music.
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.