1585 search results - page 46 / 317 » Using a Non-prior Training Active Feature Model |
139
click to vote
ICASSP
2010
IEEE
15 years 4 months ago
2010
IEEE
It has become common practice to adapt acoustic models to specific-conditions (gender, accent, bandwidth) in order to improve the performance of speech-to-text (STT) transcriptio...
121
click to vote
ACL
2011
14 years 7 months ago
2011
We investigate the use of textual Internet conversations for detecting questions in spoken conversations. We compare the text-trained model with models trained on manuallylabeled,...
170
click to vote
ANSS
2006
IEEE
15 years 10 months ago
2006
IEEE
Anomaly detection systems largely depend on user profile data to be able to detect deviation from normal activity. Most of this profile data is based on commands executed by use...
124
click to vote
CVPR
2007
IEEE
16 years 6 months ago
2007
IEEE
This paper proposes a discriminative framework for efficiently aligning images. Although conventional Active Appearance Models (AAM)-based approaches have achieved some success, t...
126
click to vote
NIPS
1994
15 years 5 months ago
1994
A self-organizing neural network for sequence classification called SARDNET is described and analyzed experimentally. SARDNET extends the Kohonen Feature Map architecture with act...