Joint Beat and Downbeat Tracking with Recurrent Neural Networks

JOINT BEAT AND DOWNBEAT TRACKING WITH RECURRENT NEURAL NETWORKS Sebastian B ̈ ock, Florian Krebs, and Gerhard Widmer Department of Computational Perception Johannes Kepler University Linz, Austria [email protected] ABSTRACT In this paper we present a novel method for jointly extract- ing beats and downbeats from audio signals. A recurrent neural network operating directly on magnitude spectro- grams is used to model the metrical structure of the audio signals at multiple levels and provides an output feature that clearly distinguishes between beats and downbeats. A dynamic Bayesian network is then used to model bars of variable length and align the predicted beat and down- beat positions to the global best solution. We find that the proposed model achieves state-of-the-art performance on a wide range of different musical genres and styles.