Modelling Perception of Speed in Music Audio
2013 (English)In: Proceedings of the Sound and Music Computing Conference 2013, 2013, 735-741 p.Conference paper (Refereed)
One of the major parameters in music is the overall speed of a musical performance. Speed is often associated with tempo, but other factors such as note density (onsets per second) seem to be important as well. In this study, a computational model of speed in music audio has been developed using a custom set of rhythmic features. The original audio is first separated into a harmonic part and a percussive part and onsets are extracted separately from the different layers. The characteristics of each onset are determined based on frequency content as well as perceptual salience using a clustering approach. Using these separated onsets a set of eight features including a tempo estimation are defined which are specifically designed for modelling perceived speed. In a previous study 20 listeners rated the speed of 100 ringtones consisting mainly of popular songs, which had been converted from MIDI to audio. The ratings were used in linear regression and PLS regression in order to evaluate the validity of the model as well as to find appropriate features. The computed audio features were able to explain about 90 % of the variability in listener ratings.
Place, publisher, year, edition, pages
2013. 735-741 p.
Computer Science Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:kth:diva-137404ISBN: 9789175018317OAI: oai:DiVA.org:kth-137404DiVA: diva2:678904
SMC Sound and Music Computing Conference 2013; Stockholm, Sweden, 30 July-3 August, 2013
QC 201402132013-12-132013-12-132014-02-13Bibliographically approved