MelodyT5: A Unified Score-to-Score Transformer for Symbolic Music Processing

TL;DR

MelodyT5 introduces a unified transformer framework for symbolic music tasks, leveraging multi-task transfer learning on a large curated dataset to improve performance across diverse music processing applications.

Contribution

It presents MelodyT5, a novel encoder-decoder model that unifies multiple symbolic music tasks as score-to-score transformations, trained on a large dataset for improved versatility.

Findings

Superior performance in symbolic music tasks via multi-task transfer learning

Effective handling of data-scarce tasks in symbolic music processing

Challenging task-specific paradigms with a unified model and dataset

Abstract

In the domain of symbolic music research, the progress of developing scalable systems has been notably hindered by the scarcity of available training data and the demand for models tailored to specific tasks. To address these issues, we propose MelodyT5, a novel unified framework that leverages an encoder-decoder architecture tailored for symbolic music processing in ABC notation. This framework challenges the conventional task-specific approach, considering various symbolic music tasks as score-to-score transformations. Consequently, it integrates seven melody-centric tasks, from generation to harmonization and segmentation, within a single model. Pre-trained on MelodyHub, a newly curated collection featuring over 261K unique melodies encoded in ABC notation and encompassing more than one million task instances, MelodyT5 demonstrates superior performance in symbolic music processing via multi-task transfer learning. Our findings highlight the efficacy of multi-task transfer learning in symbolic music processing, particularly for data-scarce tasks, challenging the prevailing task-specific paradigms and offering a comprehensive dataset and framework for future explorations in this domain.