PerceiverS: A Multi-Scale Perceiver with Effective Segmentation for Long-Term Expressive Symbolic Music Generation

TL;DR

PerceiverS introduces a novel multi-scale architecture with effective segmentation and attention mechanisms to improve long-term, expressive symbolic music generation, capturing both structure and nuance.

Contribution

The paper presents PerceiverS, a new model combining segmentation and multi-scale attention to enhance long-term structure and expressiveness in symbolic music generation.

Findings

Improved coherence and diversity in generated music

Enhanced long-term structural dependency modeling

Preservation of expressive nuances in music samples

Abstract

AI-based music generation has made significant progress in recent years. However, generating symbolic music that is both long-structured and expressive remains a significant challenge. In this paper, we propose PerceiverS (Segmentation and Scale), a novel architecture designed to address this issue by leveraging both Effective Segmentation and Multi-Scale attention mechanisms. Our approach enhances symbolic music generation by simultaneously learning long-term structural dependencies and short-term expressive details. By combining cross-attention and self-attention in a Multi-Scale setting, PerceiverS captures long-range musical structure while preserving performance nuances. The proposed model has been evaluated using the Maestro dataset and has demonstrated improvements in generating coherent and diverse music, characterized by both structural consistency and expressive variation. The project demos and the generated music samples can be accessed through the link: https://perceivers.github.io.