This paper concerns the use of speech enhancement to improve automatic speech recognition (ASR) performance in noisy environments. Speech enhancement systems are usually designed separately from a back-end recognizer by optimizing the frontend parameters with signal-level criteria. Such a disjoint processing approach is not always useful for ASR. Indeed, timefrequency masking, which is widely u...

Discontinuous Galerkin Multiscale Methods for Elliptic Problems Daniel Elfverson In this paper a continuous Galerkin multiscale method (CGMM) and a discontinuous Galerkin multiscale method (DGMM) are proposed, both based on the variational multiscale method for solving partial differential equations numerically. The solution is decoupled into a coarse and a fine scale contribution, where the fi...

A curse of dimensionality arises when using the Continuum-GMM procedure to estimate large dimensional models. Two solutions are proposed, both of which convert the high dimensional model into a continuum of reduced information sets. Under certain regularity conditions, each reduced information set can be used to produce a consistent estimator of the parameter of interest. An indirect CGMM estim...

In the Competing Interests statement, the inclusion of Carmen Binder as a Roche employee is incorrect. The publisher apologizes for the error. The correct Competing Interests statement is as follows: U-PR, HHS and CGMM are employees of F. Hoffmann-La Roche Ltd. None of the other authors have any competing interests to declare. This does not alter our adherence to PLOS ONE policies on sharing da...

In high-resolution maritime surveillance radars, sea clutter exhibits highly spatial heterogeneity due to modulation of long waves with wavelengths longer than the width one range cell. Compound-Gaussian model (CGM) fails characterize heterogeneous in both amplitude distribution and Doppler spectrum. this article, a bi-phase compound-Gaussian mixture (BP-CGMM) is proposed clutter. BP-CGMM, reso...

Many glacier-related hazards are well typified and studied, but some events stand out from conventional classifications. The Kolka-Karmadon catastrophic event on 20 September 2002 in North Ossetia, North Caucasus, Russia is used as an example of a complex glacier failure exhibiting characteristics such as high mobility, long runout, ultrarapid movement and multiphase behaviour. We consider term...

This paper focuses on the detection and segmentation of Multiple Sclerosis (MS) lesions in magnetic resonance (MRI) brain images. To capture the complex tissue spatial layout, a probabilistic model termed Constrained Gaussian Mixture Model (CGMM) is proposed based on a mixture of multiple spatially oriented Gaussians per tissue. The intensity of a tissue is considered a global parameter and is ...

When the projection of a collection of samples onto a subset of basis feature vectors has a Gaussian distribution, those samples have a generalized projective Gaussian distribution (GPGD). GPGDs arise in a variety of medical images as well as some speech recognition problems. We will demonstrate that GPGDs are better represented by continuous Gaussian mixture models (CGMMs) than finite Gaussian...

We design a novel deep learning framework for multi-channel speech recognition in two aspects. First, for the front-end, an iterative mask estimation (IME) approach based on deep learning is presented to improve the beamforming approach based on the conventional complex Gaussian mixture model (CGMM). Second, for the back-end, deep convolutional neural networks (DCNNs), with augmentation of both...