End-to-End Probabilistic Inference for Nonstationary Audio Analysis

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.

Citation

Wilkinson , W , Andersen , M , Reiss , J D , Stowell , D & Solin , A 2019 , End-to-End Probabilistic Inference for Nonstationary Audio Analysis . in 36th International Conference on Machine Learning, ICML 2019 . Proceedings of Machine Learning Research , vol. 97 , JMLR , pp. 6776–6785 , International Conference on Machine Learning , Long Beach , California , United States , 09/06/2019 . < http://proceedings.mlr.press/v97/wilkinson19a.html >

Permanent link to this item

https://urn.fi/URN:NBN:fi:aalto-202001171581

Collections

[article-cris] Perustieteiden korkeakoulu / SCI

Show all metadata