Title :
Neural speech predictors
Author :
de Figueiredo, Rui J.P. ; Akay, Enis
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of California, Irvine, CA
Abstract :
In this paper we propose a new neural network architecture that deploys and extended Kalman filter (EKF) based learning algorithm. We used the new neural network for the prediction of speech signals. Simulation results show that the neural networks leads to better performance than the well known linear predictor coefficients (LPC) that uses Levinson-Durbin algorithm.
Keywords :
Kalman filters; learning (artificial intelligence); neural nets; prediction theory; speech processing; extended Kalman filter; learning algorithm; neural network architecture; speech signal prediction; Artificial neural networks; Computer architecture; Computer networks; Equations; Laboratories; Machine intelligence; Neural networks; Neurons; Predictive models; Speech;
Conference_Titel :
Circuits and Systems for Communications, 2008. ECCSC 2008. 4th European Conference on
Conference_Location :
Bucharest
Print_ISBN :
978-1-4244-2419-1
Electronic_ISBN :
978-1-4244-2420-7
DOI :
10.1109/ECCSC.2008.4611645
