On the automatic identification of difficult examples for beat tracking: towards building new evaluation datasets

TitleOn the automatic identification of difficult examples for beat tracking: towards building new evaluation datasets
Publication TypeConference Paper
Year of Publication2012
Conference NameThe 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
AuthorsHolzapfel, A., Davies M. E. P., Zapata J., Oliveira J., & Gouyon F.
Pagination89-92
Conference Start Date25/03/2012
PublisherIEEE
Conference LocationKyoto, Japan
Keywordsbeat tracking, database
AbstractIn this paper, an approach is presented that identifies music samples which are difficult for current state-of-the-art beat trackers. In order to estimate this difficulty even for examples without ground truth, a method motivated by selective sampling is applied. This method assigns a degree of difficulty to a sample based on the mutual dis- agreement between the output of various beat tracking systems. On a large beat annotated dataset we show that this mutual agreement is correlated with the mean performance of the beat trackers evaluated against the ground truth, and hence can be used to identify difficult examples by predicting poor beat tracking performance. Towards the aim of advancing future beat tracking systems, we demonstrate how our method can be used to form new datasets containing a high proportion of challenging music examples.
intranet