Exploring Transformer's potential on automatic piano transcription

TL;DR

This paper investigates the use of Transformer models in automatic piano transcription, demonstrating improved accuracy over traditional neural network approaches on multiple datasets.

Contribution

It introduces Transformer architecture into AMT, showing its advantages for velocity detection and overall transcription accuracy compared to existing methods.

Findings

Transformer outperforms CNN-RNN models on velocity detection

Performance improves on frame-level metrics

Performance improves on note-level metrics

Abstract

Most recent research about automatic music transcription (AMT) uses convolutional neural networks and recurrent neural networks to model the mapping from music signals to symbolic notation. Based on a high-resolution piano transcription system, we explore the possibility of incorporating another powerful sequence transformation tool -- the Transformer -- to deal with the AMT problem. We argue that the properties of the Transformer make it more suitable for certain AMT subtasks. We confirm the Transformer's superiority on the velocity detection task by experiments on the MAESTRO dataset and a cross-dataset evaluation on the MAPS dataset. We observe a performance improvement on both frame-level and note-level metrics after introducing the Transformer network.