5012 search results - page 722 / 1003 » Distributed Error Correction |
166
click to vote
INTERSPEECH
2010
15 years 1 months ago
2010
Current speech recognition systems are often based on HMMs with state-clustered Gaussian Mixture Models (GMMs) to represent the context dependent output distributions. Though high...
160
click to vote
JEI
2010
2010
Estimating reflectance from multispectral camera responses based on partial least-squares regression
15 years 1 months ago
Abstract. In multispectral imaging systems, the accuracy of reflectance estimation can be degraded by the nonlinearity in imaging process, which is due to non-Gaussian distribution...
193
click to vote
TASLP
2010
15 years 1 months ago
2010
Traditional n-gram language models are widely used in state-of-the-art large vocabulary speech recognition systems. This simple model suffers from some limitations, such as overfi...
275
click to vote
Publication
This paper presents an algorithm for the classification of head pose in low resolution video. Invariance to skin, hair and background colours is achieved by classifying using an en...
205
click to vote
CORR
2011
Springer
14 years 10 months ago
2011
Springer
We initiate the study of sparse recovery problems under the Earth-Mover Distance (EMD). Specifically, we design a distribution over m × n matrices A such that for any x, given A...