Audio-to-Score Alignment Using Deep Automatic Music Transcription

TL;DR

This paper presents a novel note-level audio-to-score alignment method leveraging deep learning-based automatic music transcription and HMM-based score alignment, significantly advancing the state-of-the-art through extensive testing.

Contribution

It introduces a new approach combining deep AMT models with HMM alignment for improved note-level accuracy in audio-to-score alignment.

Findings

Achieved significant improvement over previous methods

Demonstrated robustness across multiple datasets

Provided a systematic procedure for large unaligned datasets

Abstract

Audio-to-score alignment (A2SA) is a multimodal task consisting in the alignment of audio signals to music scores. Recent literature confirms the benefits of Automatic Music Transcription (AMT) for A2SA at the frame-level. In this work, we aim to elaborate on the exploitation of AMT Deep Learning (DL) models for achieving alignment at the note-level. We propose a method which benefits from HMM-based score-to-score alignment and AMT, showing a remarkable advancement beyond the state-of-the-art. We design a systematic procedure to take advantage of large datasets which do not offer an aligned score. Finally, we perform a thorough comparison and extensive tests on multiple datasets.