Hidden Conditional Random Fields(HCRF) is a very promising approach to model speech. However, because HCRF computes the score of a hypothesis by summing up linearly weighted featu...
In this paper, a robust feature for text-independent speaker recognition is proposed, which simulate the response mode of cochlear neurons in processing acoustic signal. The featu...
Successful spectrum sharing in a cognitive radio network depends on the correct and quick detection of primary activity. Cooperative spectrum sensing is therefore suggested to enh...
Laila Hesham, Ahmed Sultan, Mohammed Nafie, Fadel ...
We introduce the Multiplicative Update Selector and Estimator (MUSE) algorithm for sparse approximation in underdetermined linear regression problems. Given f = Φα∗ + µ, the ...
We present several modifications of the original recurrent neural network language model (RNN LM). While this model has been shown to significantly outperform many competitive l...
Tomas Mikolov, Stefan Kombrink, Lukas Burget, Jan ...