Sciweavers

1293 search results - page 48 / 259
» Modelling Smooth Paths Using Gaussian Processes
Sort
View
ICASSP
2011
IEEE
13 years 2 months ago
Soft frame margin estimation of Gaussian Mixture Models for speaker recognition with sparse training data
—Discriminative Training (DT) methods for acoustic modeling, such as MMI, MCE, and SVM, have been proved effective in speaker recognition. In this paper we propose a DT method fo...
Yan Yin, Qi Li
ICASSP
2008
IEEE
14 years 5 months ago
Factorized variational approximations for acoustic multi source localization
Estimation based on received signal strength (RSS) is crucial in sensor networks for sensor localization, target tracking, etc. In this paper, we present a Gaussian approximation ...
Volkan Cevher, Aswin C. Sankaranarayanan, Rama Che...
NIPS
2003
14 years 11 days ago
Bayesian Color Constancy with Non-Gaussian Models
We present a Bayesian approach to color constancy which utilizes a nonGaussian probabilistic model of the image formation process. The parameters of this model are estimated direc...
Charles R. Rosenberg, Thomas P. Minka, Alok Ladsar...
TSP
2012
12 years 6 months ago
Distributed Covariance Estimation in Gaussian Graphical Models
—We consider distributed estimation of the inverse covariance matrix in Gaussian graphical models. These models factorize the multivariate distribution and allow for efficient d...
Ami Wiesel, Alfred O. Hero
NAACL
2004
14 years 11 days ago
Exponential Priors for Maximum Entropy Models
Maximum entropy models are a common modeling technique, but prone to overfitting. We show that using an exponential distribution as a prior leads to bounded absolute discounting b...
Joshua Goodman