Sciweavers

598 search results - page 20 / 120
» Using Uncertainty Information to Combine Soft Classification...
Sort
View
ICASSP
2011
IEEE
12 years 11 months ago
Continuous F0 in the source-excitation generation for HMM-based TTS: Do we need voiced/unvoiced classification?
Most HMM-based TTS systems use a hard voiced/unvoiced classification to produce a discontinuous F0 signal which is used for the generation of the source-excitation. When a mixed ...
Javier Latorre, Mark J. F. Gales, Sabine Buchholz,...
IH
2007
Springer
14 years 1 months ago
Soft Feature-Based Watermark Decoding with Insertion/Deletion Correction
Abstract. Hard decisions constitute the major problem in digital watermarking applications, especially when content adaptive embedding methods are used. Soft-decision decoding, on ...
Mathias Schlauweg, Dima Pröfrock, Erika M&uum...
COLING
2008
13 years 9 months ago
Choosing the Right Translation: A Syntactically Informed Classification Approach
One style of Multi-Engine Machine Translation architecture involves choosing the best of a set of outputs from different systems. Choosing the best translation from an arbitrary s...
Simon Zwarts, Mark Dras
ICDAR
2007
IEEE
13 years 11 months ago
WEB Image Classification Based on the Fusion of Image and Text Classifiers
This paper presents a novel method for the classification of images that combines information extracted from the images and contextual information. The main hypothesis is that con...
Pedro R. Kalva, Fabrício Enembreck, Alessan...
NIPS
1998
13 years 9 months ago
Robot Docking Using Mixtures of Gaussians
This paper applies the Mixture of Gaussians probabilistic model, combined with Expectation Maximization optimization to the task of summarizing three dimensional range data for a ...
Matthew M. Williamson, Roderick Murray-Smith, Volk...