120 search results - page 18 / 24 » Maximum entropy models for speech confidence estimation |
148
click to vote
ICPR
2010
IEEE
15 years 8 months ago
2010
IEEE
This paper concentrates on speech duration distributions that are usually invariant to noises and proposes a noise-robust and real-time voice activity detector (VAD) using the hid...
183
click to vote
ICASSP
2009
IEEE
16 years 1 months ago
2009
IEEE
Audio segmentation is an essential preprocessing step in several audio processing applications with a significant impact e.g. on speech recognition performance. We introduce a no...
177
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
Shannon's Noisy-Channel model, which describes how a corrupted message might be reconstructed, has been the corner stone for much work in statistical language and speech proc...
181
click to vote
CVPR
2001
IEEE
16 years 8 months ago
2001
IEEE
In this paper we describe a statistical method for the integration of an unlimited number of cues within a deformable model framework. We treat each cue as a random variable, each...
194
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
The scores returned by support vector machines are often used as a confidence measures in the classification of new examples. However, there is no theoretical argument sustaining ...