Sciweavers

4451 search results - page 265 / 891
» Continuous model synthesis
Sort
View
CSL
1999
Springer
15 years 6 months ago
The Bell Labs German text-to-speech system
In this paper we present an overview of the German version of the Bell Labs text-to-speech system, a high-quality concatenative synthesis system with extensive text analysis capab...
Bernd Möbius
ICASSP
2011
IEEE
14 years 10 months ago
A design procedure for oversampled nonuniform filter banks with perfect-reconstruction
We describe a time-domain procedure for designing the synthesis filters of perfect-reconstruction oversampled filter banks. A condition matrix is derived from the basic magnitud...
Mohamed F. Mansour
ICASSP
2011
IEEE
14 years 10 months ago
An unsupervised algorithm for hybrid/morphological signal decomposition
The main contribution presented here is an adaptive/unsupervised iterative thresholding algorithm for sparse representation of signals which can be modeled as the sum of two compo...
Matthieu Kowalski, Thomas Rodet
CVPR
2009
IEEE
16 years 1 months ago
Removing partial blur in a single image
Removing image partial blur is of great practical importance. However, as existing recovery techniques usually assume a one-layer clear image model, they can not characterize the ...
Shengyang Dai, Ying Wu
ICPR
2008
IEEE
16 years 1 months ago
Convenient reconstruction of natural plants by images
Convenient reconstruction of natural plants is a difficult task because of their intrinsic complex geometry. In this paper, we propose a convenient image-based approach to modeli...
Wei Ma, Hongbin Zha