An analysis of basic expressive qualities in instrumental conducting

Kyungho Lee, Michael J. Junokas, Mohammad Amanzadeh, Guy E. Garnett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Advances in sensing technology make the task of quantifying expressive human body movement more feasible than ever before. Success will enable breakthroughs in Humancomputer interaction (HCI) and control paradigms. In most areas, however, expressivity remains vague and difficult to define. We examine the movements of instrumental conductors at an elementary level to define particular qualities of a beat. In our test case, we focus on the difference between sostenuto and staccato articulation styles as a base for expressive qualities. We show that it is possible to define generic low-level movement features, we call movement primitives, to quantify the qualitative aspects of these two different articulation styles across a range of different tempi. Our movement primitives include the mean and variance of the magnitude of velocity and acceleration, and measures of spatial curvature. Each of these is measured from the ictus of one beat through the ictus of the next beat in a standard 4/4 beat pattern. The discriminative power of these features is demonstrated by two-tail t-tests and verified through Naïve Bayes classification experiments. The results demonstrate that our use of movement primitives effectively describes characteristics of expression revealed in each beat of two different articulation styles.

Original languageEnglish (US)
Title of host publicationMOCO 2015 - Proceedings of the 2nd International Workshop on Movement and Computing
Subtitle of host publicationIntersecting Art, Meaning, Cognition, Technology
PublisherAssociation for Computing Machinery
Pages148-155
Number of pages8
ISBN (Electronic)9781450334570
DOIs
StatePublished - Aug 14 2015
Event2nd International Workshop on Movement and Computing, MOCO 2015 - Vancouver, Canada
Duration: Aug 14 2015Aug 15 2015

Publication series

NameACM International Conference Proceeding Series
Volume14-15-August-2015

Other

Other2nd International Workshop on Movement and Computing, MOCO 2015
CountryCanada
CityVancouver
Period8/14/158/15/15

Keywords

  • Beat pattern gestures
  • Conducting gestures
  • Expressiveness
  • Feature generation
  • Gesture recognition
  • Movement primitives

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'An analysis of basic expressive qualities in instrumental conducting'. Together they form a unique fingerprint.

Cite this