Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Mid-level Chord Transition Features for Musical Style Analysis

 
: Weis, C.; Brand, F.; Müller, M.

:

Sanei, Saeid (General Chair) ; Institute of Electrical and Electronics Engineers -IEEE-; IEEE Signal Processing Society:
ICASSP 2019, IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings : May 12-17, 2019, Brighton
Piscataway, NJ: IEEE, 2019
ISBN: 978-1-4799-8131-1
ISBN: 978-1-4799-8132-8
S.341-345
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) <44, 2019, Brighton>
Englisch
Konferenzbeitrag
Fraunhofer IIS ()

Abstract
Chords and their progressions are an important tonal music. Specifically, transitions between within a piece carry style-relevant information. formation from audio recordings, a naive approa tomatic chord estimation for computing chord la then derives transition statistics. Often, this is Markov Models involving the Viterbi decoding al since chords are often ambiguous, deciding on o sequence can be problematic, which heavily aff derivation of transition features. In this paper, mid-level features that capture chord transitions i method exploits the Baum-Welch algorithm, whi hard decisions on chord labels. Instead, we obtai tures that account for ambiguities among chord tions. In several experiments, we evaluate thes style classification scenario discriminating four h Western classical music. Our soft transition fe achieve higher accuracies than comparable hard thus demonstrating the descriptive power of the n.

: http://publica.fraunhofer.de/dokumente/N-590253.html