This paper introduces our actual work in front-end techniques to obtain robust speech recognition devices in mismatch conditions (additive noise mismatch and channel mismatch). Two algorithms have been combined to compensate the distortions due to different channel characteristics and additive noise: 1) A Cepstral Mean Normalization and Variance Scaling technique (MNVS) and 2) An Adaptive Gauss...

Abstract Both varying-coefficient and additive models have been studied extensively in the literature as extensions to linear models. They have also been extended to functional response data. However, existing extensions are still not sufficiently flexible to reflect the functional feature of the responses. In this paper, we extend both varying-coefficient and additive models to a much more fle...

Metric trees are dendrograms which show the phylogenetic relationships for a set of contemporary species. These dendrograms have numerical values attached to the branches. If the sum of these values on the branches between any two contemporary species is equal to the dissimilarity between these two species, the metric tree is said to be additive and possess an additive dissimilarity matrix. Met...

Steganography is the art of message hiding in a cover signal without attracting attention. The requirements of the good steganography algorithm are security, capacity, robustness and imperceptibility, all them are contradictory, therefore, satisfying all together is not easy especially in audio cover signal because human auditory system (HAS) has high sensitivity to audio modification. In this ...

An overlapping domain decomposition, additive Schwarz, conjugate gradient method is presented for the solution of the linear systems which arise when orthogonal spline collocation with piecewise Hermite bicu-bics is applied to the Dirichlet problem for Poisson's equation on a rectangle .

The aim of the present study was the estimation of (co) variance components and genetic parameters for body weight of Moghani sheep, using random regression models based on B-Splines functions. The data set included 9165 body weight records from 60 to 360 days of age from 2811 Moghani sheep, collected between 1994 to 2013 from Jafar-Abad Animal Research and Breeding Institute, Ardabil province,...

This communication deals with the source separation problem which consists in the separation of a noisy mixture of independent sources without a priori knowledge of the mixture coeecients. In this paper, we consider the maximum likelihood (ML) approach for discrete source signals with known probability distributions. An important feature of the ML approach in Gaussian noise is that the covarian...

There are several models for sparse approximation: one where a signal is a sparse linear combination of vectors over a redundant dictionary and a second model in which a collection of signals is a simultaneous sparse linear combination over a single dictionary. In this work, interpolate between these two models to synthesize a single signal of interest from K highly incoherent dictionaries whil...