Back To Schedule
Thursday, October 28 • 9:00pm - Friday, December 3 • 6:00pm
WaveBeat: End-to-end beat and downbeat tracking in the time domain

Log in to save this to your schedule, view media, leave feedback and see who's attending!

While deep learning approaches for beat and downbeat tracking have brought advancements, these approaches continue to rely on hand-crafted, subsampled spectral features as input, restricting the information available to the model. In this work, we propose WaveBeat, an end-to-end approach for joint beat and downbeat tracking operating directly in the time domain. This method forgoes engineered spectral features, and instead produces beat and downbeat predictions directly from the waveform, the first of its kind for this task. Our model utilizes temporal convolutional networks (TCNs) operating on waveforms that achieve a very large receptive field (~30s) at audio sample rates. This is achieved in a memory efficient manner by employing rapidly growing dilation factors, which enable a relatively shallower network architecture. Combined with a straightforward data augmentation strategy, our method outperforms previous state-of-the-art methods on some datasets, while producing comparable results on others.

avatar for Christian Steinmetz

Christian Steinmetz

PhD Researcher, Centre for Digital Music, Queen Mary University of London
PhD Researcher
avatar for Joshua Reiss

Joshua Reiss

Queen Mary University of London
Josh Reiss is a Professor with the Centre for Digital Music at Queen Mary University of London. He has published more than 200 scientific papers, and co-authored the book Intelligent Music Production, and textbook Audio Effects: Theory, Implementation and Application. He is the President-Elect... Read More →

Thursday October 28, 2021 9:00pm - Friday December 3, 2021 6:00pm EST