Sciweavers

1291 search results - page 180 / 259
» Learning a language model from continuous speech
Sort
View
USS
2010
14 years 7 months ago
Acoustic Side-Channel Attacks on Printers
We examine the problem of acoustic emanations of printers. We present a novel attack that recovers what a dotmatrix printer processing English text is printing based on a record o...
Michael Backes, Markus Dürmuth, Sebastian Ger...
CMC
1998
Springer
15 years 2 months ago
The IntelliMedia WorkBench - An Environment for Building Multimodal Systems
Abstract. Intelligent MultiMedia (IntelliMedia) focuses on the computer processing and understanding of signal and symbol input from at least speech, text and visual images in term...
Tom Brøndsted, Paul Dalsgaard, Lars Bo Lars...
MM
2009
ACM
269views Multimedia» more  MM 2009»
15 years 4 months ago
Semi-supervised topic modeling for image annotation
We propose a novel technique for semi-supervised image annotation which introduces a harmonic regularizer based on the graph Laplacian of the data into the probabilistic semantic ...
Yuanlong Shao, Yuan Zhou, Xiaofei He, Deng Cai, Hu...
IROS
2008
IEEE
191views Robotics» more  IROS 2008»
15 years 4 months ago
Local Gaussian process regression for real-time model-based robot control
— High performance and compliant robot control requires accurate dynamics models which cannot be obtained analytically for sufficiently complex robot systems. In such cases, mac...
Duy Nguyen-Tuong, Jan Peters
JMLR
2010
106views more  JMLR 2010»
14 years 4 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...