Time-Frequency Scattering Accurately Models Auditory Similarities Between Instrumental Playing Techniques

TL;DR

This paper introduces a time-frequency scattering model combined with metric learning to accurately capture auditory similarities in instrumental techniques, surpassing previous methods in modeling timbre perception.

Contribution

It proposes a novel machine listening approach using joint time-frequency scattering features and LMNN metric learning to model complex timbre similarities across instruments and techniques.

Findings

Achieves 99.0% AP@5 in similarity retrieval

Outperforms existing models in modeling timbre perception

Ablation shows importance of scattering features and metric learning

Abstract

Instrumental playing techniques such as vibratos, glissandos, and trills often denote musical expressivity, both in classical and folk contexts. However, most existing approaches to music similarity retrieval fail to describe timbre beyond the so-called "ordinary" technique, use instrument identity as a proxy for timbre quality, and do not allow for customization to the perceptual idiosyncrasies of a new subject. In this article, we ask 31 human subjects to organize 78 isolated notes into a set of timbre clusters. Analyzing their responses suggests that timbre perception operates within a more flexible taxonomy than those provided by instruments or playing techniques alone. In addition, we propose a machine listening model to recover the cluster graph of auditory similarities across instruments, mutes, and techniques. Our model relies on joint time--frequency scattering features to extract spectrotemporal modulations as acoustic features. Furthermore, it minimizes triplet loss in the cluster graph by means of the large-margin nearest neighbor (LMNN) metric learning algorithm. Over a dataset of 9346 isolated notes, we report a state-of-the-art average precision at rank five (AP@5) of $99.0\%\pm1$. An ablation study demonstrates that removing either the joint time--frequency scattering transform or the metric learning algorithm noticeably degrades performance.