Cluster analysis of voice quality ratings: identifying groups of perceptually similar speakers

Abstract

Cluster analysis is a way of classifying individual cases into groups on the basis of their similarity in respect of a defined set of variables. In this investigation, our cases are 99 male speakers of Southern Standard British English, matched for age and occupation. The classifying variables are the perceptual ratings given by three phoneticians to these speakers on 32 settings of the Vocal Profile Analysis scheme, one of the most widely used protocols to assess voice quality perceptually. The results reveal that it is possible to distinguish at least two speaker clusters. The forensic implications of these results are discussed.

Publication
Proceedings of the Conference on Phonetics & Phonology in German-speaking countries (P&P 13), 28-29 September 2017, Berlin, Germany. Berlin: Humbold Universität zu Berlin, pp. 173-176