2018/11/06 by William J. Wilkinson, Michael Riis Andersen, Wilkinson, William J. +7
Computer Science · Engineering · Mathematics · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Signal Processing (eess.SP) #Sound (cs.SD) #cs.LG #cs.SD #eess.AS #eess.SP #electronic engineering #information engineering #stat.ML
paper · pdf · doi:10.48550/arxiv.1811.02489
Accepted to International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019
arxiv created 2019/02/12 · arxiv updated 2019/02/13
In audio signal processing, probabilistic time-frequency models have many benefits over their non-probabilistic counterparts. They adapt to the incoming signal, quantify uncertainty, and measure correlation between the signal's amplitude and phase information, making time domain resynthesis straightforward. However, these models are still not widely used since they come at a high computational cost, and because they are formulated in such a way that it can be difficult to interpret all the modelling assumptions. By showing their equivalence to Spectral Mixture Gaussian processes, we illuminate the underlying model assumptions and provide a general framework for constructing more complex models that better approximate real-world signals. Our interpretation makes it intuitive to inspect, compare, and alter the models since all prior knowledge is encoded in the Gaussian process kernel functions. We utilise a state space representation to perform efficient inference via Kalman smoothing, and we demonstrate how our interpretation allows for efficient parameter learning in the frequency domain.