We propose an approach for learning robust acoustic models in adverse
en...
Mathematical approaches from dynamical systems theory are used in a rang...
We propose a novel family of band-pass filters for efficient spectral
de...
Restricted Boltzmann Machines are described by the Gibbs measure of a
bi...
Speech representation and modelling in high-dimensional spaces of acoust...
We consider learning on graphs, guided by kernels that encode similarity...
We study the average case performance of multi-task Gaussian process (GP...
Statistical physics approaches can be used to derive accurate prediction...