English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

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