Sciweavers

457 search results - page 64 / 92
» Universal background model based speech recognition
Sort
View
ICPR
2010
IEEE
14 years 10 months ago
A Probabilistic Language Model for Hand Drawings
Probabilistic language models are critical to applications in natural language processing that include speech recognition, optical character recognition, and interfaces for text e...
Abdullah Akce, Timothy Bretl
ICASSP
2011
IEEE
14 years 1 months ago
Lattice-based unsupervised acoustic model training
Unsupervised acoustic model training has been successfully used to improve the performance of automatic speech recognition systems when only a small amount of manually transcribed...
Thiago Fraga-Silva, Jean-Luc Gauvain, Lori Lamel
CVPR
1999
IEEE
15 years 12 months ago
Object Recognition with Color Cooccurrence Histograms
We use the color cooccurrence histogram (CH) for recognizing objects in images. The color CH keeps track of the number of pairs of certain colored pixels that occur at certain sep...
Peng Chang, John Krumm
ICCV
2003
IEEE
15 years 11 months ago
Learning Pedestrian Models for Silhouette Refinement
We present a model-based method for accurate extraction of pedestrian silhouettes from video sequences. Our approach is based on two assumptions, 1) there is a common appearance t...
L. Lee, Gerald Dalley, Kinh Tieu
ASIAMS
2007
IEEE
15 years 4 months ago
Rough-Fuzzy Granulation, Rough Entropy and Image Segmentation
This talk has two parts explaining the significance of Rough sets in granular computing in terms of rough set rules and in uncertainty handling in terms of lower and upper approxi...
Sankar K. Pal