A system for improving the communication of emotion in music performance by feedback learning
2002 (English)In: JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, Vol. 111, 2471- p.Article in journal (Refereed) Published
Expressivity is one of the most important aspects of music performance. However, in music education, expressivity is often overlooked in favour of technical abilities. This could possibly depend on the difficulty in describing expressivity, which makes it problematic to provide the student with specific feedback. The aim of this project is to develop a computer program, which will improve the student’s ability in communicating emotion in music performance. The expressive intention of a performer can be coded in terms of performance parameters (cues), such as tempo, sound level, timbre, and articulation. Listeners’ judgements can be analyzed in the same terms. An algorithm was developed for automatic cue extraction from audio signals. Using note onset-offset detection, the algorithm yields values of sound level, articulation, IOI, and onset velocity for each note. In previous research, Juslin has developed a method for quantitative evaluation of performer-listener communication. This framework forms the basis of the present program. Multiple regression analysis on performances of the same musical fragment, played with different intentions, determines the relative importance of each cue and the consistency of cue utilization. Comparison with built-in listener models, simulating perceived expression using a regression equation, provides detailed feedback regarding the performer’s cue utilization.
Place, publisher, year, edition, pages
2002. Vol. 111, 2471- p.
music, performance, computer, feedback, algorithm
IdentifiersURN: urn:nbn:se:uu:diva-45627OAI: oai:DiVA.org:uu-45627DiVA: diva2:73535