Department of Computational Perception

Analysis of Musical Interpretation: Herbert von Karajan

Full Project Title: Towards Interdisciplinary, Computer-assisted Analysis of Musical Interpretation: A Study on the Art of Herbert von Karajan

Sponsor: Austrian Science Fund (Fonds zur Förderung der wissenschaftlichen Forschung, FWF)

Project Number: P 29840-G26

Duration: 36 months (June 2017 - June 2020)

Central Project Website (hosted by the Eliette and Herbert von Karajan Institute)

Persons involved at our institute:

• Gerhard Widmer (Principal Investigator)
  
• Thassilo Gadermaier (Researcher)

Project Partners

• University of Music and Performing Arts Graz (KUG): Peter Revers (Project Leader), Klaus Aringer
• Dept. of Computational Perception, Johannes Kepler University Linz: Gerhard Widmer
• Eliette and Herbert von Karajan Institute, Salzburg: Matthias Röder
• Mozarteum University Salzburg: Joachim Brügge, Rainer Schwob
• Anton Bruckner Private University Linz: Lars Laubhold

Abstract

The project sets out to accomplish a data-driven study in musical interpretation, connecting information from human analyses of a number of performances by Karajan, with algorithmically derived data spanning several decades of recordings. Although the project is conceived as a case study on Karajan, we wish to demonstrate the promise of data-intensive, interdisciplinary approaches to musicological studies of expressive performance, and help in establishing this as a new open standard approach in empirical musicology. Thus our goals are:

• to compile and exploit a large database of musical recordings, meta-data, performance-measurements, analysis results,
• to combine the knowledge of experienced musicologists with new means of data capturing, analysis and pattern discovery offered by the latest development in computer science and machine learning,and
• to build an infrastructure to provide experimental and measurement data to the world of science and music scholarship at large.

Our approach goes beyond already existing projects (e.g., the Mazurka Project) in that we focus, for the first time, exclusively on orchestral music conducted by a specific performance artist. In addition to musicological and computational research results, the project has access to a unique collection of largely unpublished music and extra-musical sources (hosted by the Karajan Institute, Salzburg): 1,800 digitized recordings from 1939 to 1989, 100 recordings of rehearsals, 700 studio recordings, 1,000 concert recordings, concert films, rehearsal documentaries, letters and phone conversations by Karajan about the production process. Musicological research will be performed along several lines, with the help of computational methods of performance analysis and visualisation:

• Comparative analysis of Karajan's interpretations of the same composition from different time periods;
• Comparative analyses of tempi, articulation and orchestral balance in selected performances of orchestral works by Karajan and other contemporary conductors;
• Aesthetic evaluation and analysis of a specific 'Karajan profile' as conductor and media artist;

In parallel, computational methods for performance analysis will be developed and/or further refined, in particular,

• Algorithms for aligning performances to scores, and performances to alternative performances, to support performance (timing) analysis and comparative analysis of recordings;
• Methods for automatic extraction of performance-relevant parameters from audio recordings and audio/score alignments;
• Methods for visualizing aspects of specific orchestral recordings, to support musicologists in their analysis and search for informative passages; and
• Algorithms for automatic discovery and characterization of passages with marked differences in articulation, sound balance, treatment of instrument groups, etc.

This is a truly inter-disciplinary project, involving experienced musicologists from music and arts universities, and computer scientists with extensive experience in computer-based music performance research.

Publications

Journals

soon to come

Peer-Reviewed Conference and Workshop Proceedings

soon to come