MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

The Shape of Music. Computational Specification of Hand Gestures in Piano Playing.

Author(s)
Lamprou, Aikaterini
Thumbnail
DownloadThesis PDF (6.786Mb)
Advisor
Knight, Terry W.
Davis, Randall
Terms of use
In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/
Metadata
Show full item record
Abstract
Essential parts of human communication, expression, and productive action rely on gestures. Examining these gestures is central to design and to understanding creativity. However, techniques and skills manifested in human hand gestures are hard to capture in computational terms. In this research, I investigated how skilled hand gestures can be described computationally and apprehended visually as shapes. A case study was carried out on piano performance. I explored piano hand gestures in terms of technique and expressive intent, essential elements of the pianist’s playing style. I designed and ran a controlled study to capture gesture variation in performances of the same music, with six proficient piano players participating in the recordings. I developed technical workflows and processes to record multimodal performance data, including video, audio, MIDI and 3D motion capture, and prepared the data for visualization and analysis. I compared two performers’ piano techniques from their executions of technical exercises and detected elements of expression in a pianist’s performances of Prelude in C Minor, BWV.999 by J.S. Bach. Experts evaluated the performances from audio and video. From their comments, I extracted qualities of technique and expression essential in piano playing. Then, I determined features to measure these qualities in the motion and MIDI data. I explored the recorded data by calculating the features for different partitions of the music score. I developed feature visualizations displaying the pianists’ playing patterns. To exemplify how motion and music data could be decomposed into gestures, I presented an outline for a shape grammar for parsing musical performances. I concluded that expressive patterns detected in the played music and hand motion could be combined to identify and study gestures according to stylistic elements of piano performance. Overall, the study points towards a perceptual approach to determining and analyzing skilled hand gestures in piano playing and beyond.
Date issued
2023-06
URI
https://hdl.handle.net/1721.1/151590
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science; Massachusetts Institute of Technology. Department of Architecture
Publisher
Massachusetts Institute of Technology

Collections
  • Graduate Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.