nonlinear adaptive.pdf (204.48 kB)
0/0

Nonlinear adaptive prediction of speech with a pipelined recurrent neural network

Download (204.48 kB)
journal contribution
posted on 18.01.2010 by Jens Baltersee, Jonathon Chambers
New learning algorithms for an adaptive nonlinear forward predictor that is based on a pipelined recurrent neural network (PRNN) are presented. A computationally efficient gradient descent (GD) learning algorithm, together with a novel extended recursive least squares (ERLS) learning algorithm, are proposed. Simulation studies based on three speech signals that have been made public and are available on the World Wide Web (WWW) are used to test the nonlinear predictor. The gradient descent algorithm is shown to yield poor performance in terms of prediction error gain, whereas consistently improved results are achieved with the ERLS algorithm. The merit of the nonlinear predictor structure is confirmed by yielding approximately 2 dB higher prediction gain than a linear structure predictor that employs the conventional recursive least squares (RLS) algorithm.

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Citation

BALTERSEE, J. and CHAMBERS, J., 1998. Nonlinear adaptive prediction of speech with a pipelined recurrent neural network. IEEE Transactions on Signal Processing, 46 (8), pp. 2207-2216

Publisher

© IEEE

Version

VoR (Version of Record)

Publication date

1998

Notes

This is an article from the journal, IEEE Transactions on Signal Processing [© IEEE]. It is also available at: http://ieeexplore.ieee.org/ Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

ISSN

1053-587X

Language

en

Exports

Logo branding

Exports