Selective sampling for beat tracking evaluation

Holzapfel, Andre; Davies, Matthew E. P.; Zapata González, José Ricardo; Lobato Oliveira, João; Gouyon, Fabien

doi:http://dx.doi.org/10.1109/TASL.2012.2205244

Selective sampling for beat tracking evaluation

Citation

Holzapfel A, Davies MEP, Zapata JR, Oliveira J, Gouyon F. Selective sampling for beat tracking evaluation. IEEE Trans Audio Speech Lang Process. 2012;20(9):2539-48. DOI: 10.1109/TASL.2012.2205244

Abstract

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.