Sciweavers

248 search results - page 33 / 50
» Whole word discriminative point process models
Sort
View
ICASSP
2011
IEEE
13 years 4 days ago
Front-end feature transforms with context filtering for speaker adaptation
Feature-space transforms such as feature-space maximum likelihood linear regression (FMLLR) are very effective speaker adaptation technique, especially on mismatched test data. In...
Jing Huang, Karthik Visweswariah, Peder A. Olsen, ...
INFSOF
2007
145views more  INFSOF 2007»
13 years 8 months ago
Metrics for data warehouse conceptual models understandability
Due to the principal role of Data warehouses (DW) in making strategy decisions, data warehouse quality is crucial for organizations. Therefore, we should use methods, models, tech...
Manuel A. Serrano, Juan Trujillo, Coral Calero, Ma...
SI3D
1992
ACM
14 years 14 days ago
Lights from Highlights and Shadows
Designing the illumination of a scene is a di cult task because one needs to render the whole scene in order to look at the result. Obtaining the correct lighting e ects may requi...
Pierre Poulin, Alain Fournier
JUCS
2008
130views more  JUCS 2008»
13 years 8 months ago
Experimenting the Automated Selection of COTS Components Based on Cost and System Requirements
: In a component-based development process the selection of components is an activity that takes place over multiple lifecycle phases that span from requirement specifications thro...
Vittorio Cortellessa, Ivica Crnkovic, Fabrizio Mar...
IJPRAI
2008
235views more  IJPRAI 2008»
13 years 8 months ago
Shape-Based Individual/Group Detection for Sport Videos Categorization
We present a shape based method for automatic people detection and counting without any assumption or knowledge of camera motion. The proposed method is applied to athletic videos...
Costas Panagiotakis, Emmanuel Ramasso, Georgios Tz...