我要吃瓜

Conference Paper (published)

Real-time Speech Modeling Using Computationally Efficient Locally Recurrent Neural Networks (CERNs)

Details

Citation

Soraghan JJ, Hussain A & Shim I (1999) Real-time Speech Modeling Using Computationally Efficient Locally Recurrent Neural Networks (CERNs). In: Proceedings of Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99). Sixth European Conference on Speech Communication and Technology (EUROSPEECH'99), Budapest, Hungary, 05.09.1999-09.09.1999. Baixas, France: International Speech Communication Association, pp. 355-358. http://www.isca-speech.org/archive/eurospeech_1999/e99_0355.html

Abstract
A general class of Computationally Efficient locally Recurrent Networks (CERN) is described for real-time adaptive signal processing. The structure of the CERN is based on linear-in-the-parameters single-hidden-layered 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.

StatusPublished
Publication date31/12/1999
Publication date online30/09/1999
Related URLs
PublisherInternational Speech Communication Association
Publisher URL
Place of publicationBaixas, France
ConferenceSixth European Conference on Speech Communication and Technology (EUROSPEECH'99)
Conference locationBudapest, Hungary
Dates