Sciweavers

78 search results - page 7 / 16
» Influence of weight-decay training in input selection method...
Sort
View
96
Voted
ICASSP
2009
IEEE
15 years 4 months ago
Using a pitch-synchronous residual codebook for hybrid HMM/frame selection speech synthesis
This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so a...
Thomas Drugman, Alexis Moinet, Thierry Dutoit, Geo...
ICDM
2010
IEEE
128views Data Mining» more  ICDM 2010»
14 years 7 months ago
User-Based Active Learning
Active learning has been proven a reliable strategy to reduce manual efforts in training data labeling. Such strategies incorporate the user as oracle: the classifier selects the m...
Christin Seifert, Michael Granitzer
93
Voted
NIPS
2007
14 years 11 months ago
Sparse Feature Learning for Deep Belief Networks
Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the ra...
Marc'Aurelio Ranzato, Y-Lan Boureau, Yann LeCun
CVPR
2010
IEEE
15 years 5 months ago
Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback
Multi-class classification schemes typically require human input in the form of precise category names or numbers for each example to be annotated – providing this can be impra...
Ajay Joshi, Fatih Porikli, Nikolaos Papanikolopoul...
ICIP
2010
IEEE
14 years 7 months ago
Fast pedestrian detection with multi-scale orientation features and two-stage classifiers
In this paper, we propose an approach for fast pedestrian detection in images. Inspired by the histogram of oriented gradient (HOG) features, a set of multi-scale orientation (MSO...
Qixiang Ye, Jianbin Jiao, Baochang Zhang