Deep scattering transform applied to note onset detection and instrument recognition

TL;DR

This paper explores the use of deep scattering transforms for improving note onset detection and instrument recognition in automatic music transcription, demonstrating superior performance over traditional methods.

Contribution

It introduces the application of multiscale scattering operators to AMT tasks, showing their effectiveness on plucked string and piano music compared to classical sound representations.

Findings

Scattering outperforms classical representations in onset detection.

Scattering provides more invariant and richer sound features.

Results are validated on both MIDI-driven and real musical datasets.

Abstract

Automatic Music Transcription (AMT) is one of the oldest and most well-studied problems in the field of music information retrieval. Within this challenging research field, onset detection and instrument recognition take important places in transcription systems, as they respectively help to determine exact onset times of notes and to recognize the corresponding instrument sources. The aim of this study is to explore the usefulness of multiscale scattering operators for these two tasks on plucked string instrument and piano music. After resuming the theoretical background and illustrating the key features of this sound representation method, we evaluate its performances comparatively to other classical sound representations. Using both MIDI-driven datasets with real instrument samples and real musical pieces, scattering is proved to outperform other sound representations for these AMT subtasks, putting forward its richer sound representation and invariance properties.