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

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-11
Main Authors: Lostanlen, Vincent, El-Hajj, Christian, Rossignol, Mathias, Lafay, Grégoire, Andén, Joakim, Lagrange, Mathieu
Format: Article
Language:English
Subjects:
Ablation
Algorithms
Cluster analysis
Feature extraction
Machine learning
Music
Performance degradation
Playing techniques
Scattering
Similarity
Taxonomy
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422