Navigating Descriptive Sub-Representations of Musical Timbre

Spyridon Stasis, Jason Hockman, and Ryan Stables

Proceedings of the International Conference on New Interfaces for Musical Expression

Abstract:

Musicians, audio engineers and producers often make use of common timbral adjectives to describe musical signals and transformations. However, the subjective nature of these terms, and the variability with respect to musical context often leads to inconsistencies in their definition. In this study, a model is proposed for controlling an equaliser by navigating clusters of datapoints, which represent grouped parameter settings with the same timbral description. The interface allows users to identify the nearest cluster to their current parameter setting and recommends changes based on its relationship to a cluster centroid. To do this, we apply dimensionality reduction to a dataset of equaliser curves described as warm and bright using a stacked autoencoder, then group the entries using an agglomerative clustering algorithm with a coherence based distance criterion. To test the efficacy of the system, we implement listening tests and show that subjects are able to match datapoints to their respective sub-representations with 93.75% mean accuracy.

Citation:

Spyridon Stasis, Jason Hockman, and Ryan Stables. 2017. Navigating Descriptive Sub-Representations of Musical Timbre. Proceedings of the International Conference on New Interfaces for Musical Expression. DOI: 10.5281/zenodo.1176171

BibTeX Entry:

  @inproceedings{sstasis2017,
 abstract = {Musicians, audio engineers and producers often make use of common timbral adjectives to describe musical signals and transformations. However, the subjective nature of these terms, and the variability with respect to musical context often leads to inconsistencies in their definition. In this study, a model is proposed for controlling an equaliser by navigating clusters of datapoints, which represent grouped parameter settings with the same timbral description. The interface allows users to identify the nearest cluster to their current parameter setting and recommends changes based on its relationship to a cluster centroid. To do this, we apply dimensionality reduction to a dataset of equaliser curves described as warm and bright using a stacked autoencoder, then group the entries using an agglomerative clustering algorithm with a coherence based distance criterion. To test the efficacy of the system, we implement listening tests and show that subjects are able to match datapoints to their respective sub-representations with 93.75% mean accuracy.},
 address = {Copenhagen, Denmark},
 author = {Spyridon Stasis and Jason Hockman and Ryan Stables},
 booktitle = {Proceedings of the International Conference on New Interfaces for Musical Expression},
 doi = {10.5281/zenodo.1176171},
 issn = {2220-4806},
 pages = {56--61},
 publisher = {Aalborg University Copenhagen},
 title = {Navigating Descriptive Sub-Representations of Musical Timbre},
 url = {http://www.nime.org/proceedings/2017/nime2017_paper0012.pdf},
 year = {2017}
}