Enhanced peak picking for onset detection with recurrent neural networks

TitleEnhanced peak picking for onset detection with recurrent neural networks
Publication TypeConference Paper
Year of Publication2013
AuthorsBöck, S, Schlüter, J, Widmer, G
Conference NameProceedings of the 6th International Workshop on Machine Learning and Music
Date PublishedSeptember
Conference LocationPrague, Czech Republic
Keywordsonset detection, peak-picking
Abstract

We present a new neural network based peak-picking algorithm for common onset detection functions. Compared to existing hand-crafted methods it yields a better performance and leads to a much lower number of false negative detections. The performance is evaluated on basis of a huge dataset with over 25k annotated onsets and shows a significant improvement over existing methods in cases of signals with previously unknown levels.