Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

A crowdsourced experiment for tempo estimation of electronic dance music

 
: Schreiber, H.; Müller, M.

Gomez, E. ; International Society for Music Information Retrieval -ISMIR-:
19th International Society for Music Information Retrieval Conference, ISMIR 2018. Proceedings : Paris, France, September 23-27, 2018
Paris, 2018
ISBN: 978-2-9540351-2-3
S.409-415
International Society for Music Information Retrieval (ISMIR Conference) <19, 2018, Paris>
Englisch
Konferenzbeitrag
Fraunhofer IIS ()

Abstract
Relative to other datasets, state-of-the-art tempo estimation algorithms perform poorly on the GiantSteps Tempo dataset for electronic dance music (EDM). In order to investigate why, we conducted a large-scale, crowdsourced experiment involving 266 participants from two distinct groups. The quality of the collected data was evaluated with regard to the participants’ input devices and background. In the data itself we observed significant tempo ambiguities, which we attribute to annotator subjectivity and tempo instability. As a further contribution, we then constructed new annotations consisting of tempo distributions for each track. Using these annotations, we reevaluated two recent state-of-the-art tempo estimation systems achieving significantly improved results. The main conclusions of this investigation are that current tempo estimation systems perform better than previously thought and that evaluation quality needs to be improved. The new crowdsourced annotations will be released for evaluation purposes.

: http://publica.fraunhofer.de/dokumente/N-590268.html