University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Clustering expressive timing with regressed polynomial coefficients demonstrated by a model selection test

Li, S, Dixon, S and Plumbley, Mark (2017) Clustering expressive timing with regressed polynomial coefficients demonstrated by a model selection test In: 18th International Society for Music Information Retrieval Conference, 23 - 27 October 2017, Suzhou, China.

[img]
Preview
Text
LiDixonPlumbley17-ismir_accepted_ccby.pdf - Accepted version Manuscript

Download (165kB) | Preview

Abstract

Though many past works have tried to cluster expressive timing within a phrase, there have been few attempts to cluster features of expressive timing with constant dimen- sions regardless of phrase lengths. For example, used as a way to represent expressive timing, tempo curves can be regressed by a polynomial function such that the num- ber of regressed polynomial coefficients remains constant with a given order regardless of phrase lengths. In this paper, clustering the regressed polynomial coefficients is proposed for expressive timing analysis. A model selec- tion test is presented to compare Gaussian Mixture Models (GMMs) fitting regressed polynomial coefficients and fit- ting expressive timing directly. As there are no expect- ed results of clustering expressive timing, the proposed method is demonstrated by how well the expressive tim- ing are approximated by the centroids of GMMs. The re- sults show that GMMs fitting the regressed polynomial co- efficients outperform GMMs fitting expressive timing di- rectly. This conclusion suggests that it is possible to use regressed polynomial coefficients to represent expressive timing within a phrase and cluster expressive timing with- in phrases of different lengths.

Item Type: Conference or Workshop Item (Conference Poster)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Li, SUNSPECIFIEDUNSPECIFIED
Dixon, SUNSPECIFIEDUNSPECIFIED
Plumbley, Markm.plumbley@surrey.ac.ukUNSPECIFIED
Date : 27 October 2017
Copyright Disclaimer : ⃝c Shengchen Li, Simon Dixon, Mark D. Plumbley. Li- censed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). Attribution: Shengchen Li, Simon Dixon, Mark D. Plumbley. “Clustering expressive timing with regressed polynomial co- efficients demonstrated by a model selection test”, 18th International So- ciety for Music Information Retrieval Conference, Suzhou, China, 2017.
Depositing User : Melanie Hughes
Date Deposited : 18 Jul 2017 14:10
Last Modified : 18 Jul 2017 14:10
URI: http://epubs.surrey.ac.uk/id/eprint/841699

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800