3716 search results - page 241 / 744 » On the monotonization of the training set |
150
click to vote
ICASSP
2009
IEEE
16 years 1 months ago
2009
IEEE
Training accurate acoustic models typically requires a large amount of transcribed data, which can be expensive to obtain. In this paper, we describe a novel semi-supervised learn...
190
click to vote
ICASSP
2009
IEEE
16 years 1 months ago
2009
IEEE
Gaussian mixture model - universal background model (GMMUBM) is a standard reference classifier in speaker verification. We have recently proposed a simplified model using vect...
179
click to vote
ICDAR
2009
IEEE
16 years 1 months ago
2009
IEEE
Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, inc...
203
click to vote
CAIP
2009
Springer
16 years 1 months ago
2009
Springer
Using statistical textons for texture classification has shown great success recently. The maximal response 8 (MR8) method, which extracts an 8-dimensional feature set from 38 filt...
171
click to vote
CIKM
2009
Springer
16 years 1 months ago
2009
Springer
Recently there has been increasing interest in the problem of transfer learning, in which the typical assumption that training and testing data are drawn from identical distributi...