Selective sampling for beat tracking evaluation
2012 (English)In: IEEE Transactions on Audio, Speech and Language Processing, Vol. 20, no 9, 2539-2548 p.Article in journal (Refereed) Published
In this paper, we propose a method that can identify challenging music samples for beat tracking without ground truth. Our method, motivated by the machine learning method "selective sampling," is based on the measurement of mutual agreement between beat sequences. In calculating this mutual agreement we show the critical influence of different evaluation measures. Using our approach we demonstrate how to compile a new evaluation dataset comprised of difficult excerpts for beat tracking and examine this difficulty in the context of perceptual and musical properties. Based on tag analysis we indicate the musical properties where future advances in beat tracking research would be most profitable and where beat tracking is too difficult to be attempted. Finally, we demonstrate how our mutual agreement method can be used to improve beat tracking accuracy on large music collections.
Place, publisher, year, edition, pages
IEEE Press, 2012. Vol. 20, no 9, 2539-2548 p.
Beat tracking; evaluation; ground truth annotation; selective sampling
Research subject Media Technology
IdentifiersURN: urn:nbn:se:kth:diva-193754DOI: 10.1109/TASL.2012.2205244ISI: 000308108900004ScopusID: 2-s2.0-84865681012OAI: oai:DiVA.org:kth-193754DiVA: diva2:1040421
QC 201610312016-10-272016-10-102016-11-11Bibliographically approved