Sciweavers

473 search results - page 79 / 95
» Character Recognition using Spiking Neural Networks
Sort
View
ICASSP
2011
IEEE
12 years 11 months ago
A multi-stream ASR framework for BLSTM modeling of conversational speech
We propose a novel multi-stream framework for continuous conversational speech recognition which employs bidirectional Long Short-Term Memory (BLSTM) networks for phoneme predicti...
Martin Wöllmer, Florian Eyben, Björn Sch...
CVPR
2008
IEEE
13 years 9 months ago
Demosaicking recognition with applications in digital photo authentication based on a quadratic pixel correlation model
Most digital still color cameras use a single electronic sensor (CCD or CMOS) overlaid with a color filter array. At each pixel location only one color sample is taken, and the ot...
Yizhen Huang, Yangjing Long
ICANN
2009
Springer
13 years 5 months ago
Mental Tasks Classification for a Noninvasive BCI Application
Mapping brain activity patterns in external actions has been studied in recent decades and is the base of a brain-computer interface. This type of interface is extremely useful for...
Alexandre Ormiga G. Barbosa, David Ronald A. Diaz,...
TNN
2010
227views Management» more  TNN 2010»
13 years 2 months ago
Self-Organizing MultiLayer Perceptron
Abstract--A set of Artificial Neural Network (ANN) based methods for the design of an effective system of speech recognition of numerals of Assamese language captured under varied ...
B. Gas
WWW
2005
ACM
14 years 8 months ago
Boosting SVM classifiers by ensemble
By far, the support vector machines (SVM) achieve the state-of-theart performance for the text classification (TC) tasks. Due to the complexity of the TC problems, it becomes a ch...
Yan-Shi Dong, Ke-Song Han