Online Real-time Onset Detection with Recurrent Neural Networks

Sebastian Böck; Andreas Arzt; Florian Krebs; Markus Schedl
DAFx-2012 - York
We present a new onset detection algorithm which operates online in real time without delay. Our method incorporates a recurrent neural network to model the sequence of onsets based solely on causal audio signal information. Comparative performance against existing state-of-the-art online and offline algorithms was evaluated using a very large database. The new method – despite being an online algorithm – shows performance only slightly short of the best existing offline methods while outperforming standard approaches.
Download