Sixth European Conference on Speech Communication and Technology

A general class of Computationally Efficient locally Recurrent Networks (CERN) is described for realtime adaptive signal processing. The structure of the CERN is based on linearintheparameters singlehiddenlayered feedforward neural networks such as the Radial Basis Function (RBF) network, the Volterra Neural Network (VNN) and the recently developed Functionally Expanded Neural Network (FENN), adapted to employ local output feedback. The corresponding learning algorithms are described and key structural and computational complexity comparisons are made between the CERN and conventional Recurrent Neural Networks. A speech signal is used, which shows that a Recurrent FENN based adaptive CERN predictor can significantly outperform the corresponding feedforward FENN and conventionally employed linear adaptive filtering models.
Full Paper (PDF) GnuZipped Postscript
Bibliographic reference. Soraghan, John J. / Hussain, Amir / Shim, Ivy (1999): "Realtime speech modeling using computationally efficient locally recurrent neural networks (CERNs)", In EUROSPEECH'99, 355358.