Title :
Selective Sampling for Beat Tracking Evaluation
Author :
Holzapfel, André ; Davies, Matthew E P ; Zapata, José R. ; Oliveira, João Lobato ; Gouyon, Fabien
Author_Institution :
INESC TEC, Porto, Portugal
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.
Keywords :
learning (artificial intelligence); music; signal sampling; beat sequences; beat tracking evaluation; machine learning method; music collection; music sample; musical properties; mutual agreement; selective sampling; tag analysis; Accuracy; Correlation; Electronic mail; Estimation; Europe; Histograms; Humans; Beat tracking; evaluation; ground truth annotation; selective sampling;
Journal_Title :
Audio, Speech, and Language Processing, IEEE Transactions on
DOI :
10.1109/TASL.2012.2205244