End-to-End Probabilistic Inference for Nonstationary Audio Analysis
William Wilkinson · Michael Riis Andersen · Joshua D. Reiss · Dan Stowell · Arno Solin

Wed Jun 12th 06:30 -- 09:00 PM @ Pacific Ballroom #217

A typical audio signal processing pipeline includes multiple disjoint analysis stages, including calculation of a time-frequency representation followed by spectrogram-based feature analysis. We show how time-frequency analysis and nonnegative matrix factorisation can be jointly formulated as a spectral mixture Gaussian process model with nonstationary priors over the amplitude variance parameters. Further, we formulate this nonlinear model's state space representation, making it amenable to infinite-horizon Gaussian process regression with approximate inference via expectation propagation, which scales linearly in the number of time steps and quadratically in the state dimensionality. By doing so, we are able to process audio signals with hundreds of thousands of data points. We demonstrate, on various tasks with empirical data, how this inference scheme outperforms more standard techniques that rely on extended Kalman filtering.

Author Information

William Wilkinson (Queen Mary University of London)
Michael Andersen (Technical University of Denmark)
Joshua D. Reiss (Queen Mary University of London)
Dan Stowell (Queen Mary University of London)
Arno Solin (Aalto University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors