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

John J. Soraghan; Amir Hussain; Ivy Shim

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

John J. Soraghan^*
, Amir Hussain^*
, Ivy Shim

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

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.

Original language	English
Pages	355-358
Number of pages	4
State	Published - 1999
Externally published	Yes
Event	6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 - Budapest, Hungary Duration: 5 Sep 1999 → 9 Sep 1999

Conference

Conference	6th European Conference on Speech Communication and Technology, EUROSPEECH 1999
Country/Territory	Hungary
City	Budapest
Period	5/09/99 → 9/09/99

Bibliographical note

Publisher Copyright:
© 1999 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999. All rights reserved.

ASJC Scopus subject areas

Computer Science Applications
Software
Linguistics and Language
Communication

Cite this

@conference{c607167cc8014efc9ccd3598b26d1344,

title = "Real-time Speech Modeling using Computationally Efficient Locally Recurrent Neural Networks (CERNs)",

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.",

author = "Soraghan, \{John J.\} and Amir Hussain and Ivy Shim",

note = "Publisher Copyright: {\textcopyright} 1999 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999. All rights reserved.; 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999 ; Conference date: 05-09-1999 Through 09-09-1999",

year = "1999",

language = "English",

pages = "355--358",

}

TY - CONF

T1 - Real-time Speech Modeling using Computationally Efficient Locally Recurrent Neural Networks (CERNs)

AU - Soraghan, John J.

AU - Hussain, Amir

AU - Shim, Ivy

PY - 1999

Y1 - 1999

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85135253402

M3 - Paper

AN - SCOPUS:85135253402

SP - 355

EP - 358

T2 - 6th European Conference on Speech Communication and Technology, EUROSPEECH 1999

Y2 - 5 September 1999 through 9 September 1999

ER -

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

Abstract

Conference

Bibliographical note

ASJC Scopus subject areas

Fingerprint

Cite this