Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Timbre-invariant audio features for style analysis of classical music

 
: Weiss, Christof

:
Volltext (PDF; )

Georgaki, A. ; International Computer Music Association -ICMA-:
Music technology meets philosophy. From digital echos to virtual echos. Vol.2 : Proceedings of the ICMC/SMC 2014, 40th International Computer Music Conference joint with the 11th Sound and Music Computing Conference, 14 - 20 September 2014, Athens, Greece
San Francisco, Calif.: ICMA, 2014
ISBN: 0-9845274-3-5
ISBN: 978-0-9845274-3-4
ISBN: 978-960-466-137-4
ISBN: 978-960-7313-29-4
ISBN: 978-960-466-136-7
ISBN: 978-960-7313-28-7
S.1461-1468
International Computer Music Conference (ICMC) <40, 2014, Athens>
Sound and Music Computing Conference (SMC) <11, 2014, Athens>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IDMT ()
tonality; classification; music genre classification; music style analysis; tonality analysis

Abstract
We propose a novel set of chroma-based audio features inspired by pitch class set theory and show their utility for style analysis of classical music by using them to classify recordings into historical periods. Musicologists have long studied how composers’ styles develop and influence each other, but usually based on manual analyses of the score or, more recently, automatic analyses on symbolic data, both largely independent from timbre. Here, we investigate whether such musical style analyses can be realized using audio features. Based on chroma, our features describe the use of intervals and triads on multiple time scales. To test the efficacy of this approach we use a 1600 track balanced corpus that covers the Baroque, Classical, Romantic and Modern eras, and calculate features based on four different chroma extractors and several parameter configurations. Using Linear Discriminant Analysis, our features allow for a visual separation of the four eras that is invariant to timbre. Classification using Support Vector Machines shows that a high era classification accuracy can be achieved despite strong timbral variation (piano vs. orchestra) within eras. Under the optimal parameter configuration, the classifier achieves accuracies of 82.5%.

: http://publica.fraunhofer.de/dokumente/N-345666.html