Committees of RBFN - A novel connectionist model for speech recognition

S. Meenakshisundaram*, W. L. Woo, S. S. Dlay

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this paper we present a novel paradigm of Artificial Intelligent (AI) connectionist model namely committee machine architecture (CM) using Radial Basis Functions (RBFN) for speech recognition applications. The architecture and training scheme associated with the CM is presented. Then the performance evaluation based on the theory is given and the analysis results are verified for conformance. Importantly we have achieved 10 % improvement on word recognition rate over the best connectionist methods and an impressive 18.082 % over the baseline HMM. Critically the error rate is reduced by 10.61% over other connectionist models and 23.29 % over baseline HMM method.

Original languageEnglish
Title of host publicationProceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing
EditorsA.P. Pobil
PublisherACTA Press
Pages300-304
Number of pages5
ISBN (Print)0889864586
Publication statusPublished - 27 Dec 2004
EventProceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing - Marbella, Spain
Duration: 1 Sep 20043 Sep 2004

Conference

ConferenceProceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing
CountrySpain
CityMarbella
Period1/09/043/09/04

Fingerprint Dive into the research topics of 'Committees of RBFN - A novel connectionist model for speech recognition'. Together they form a unique fingerprint.

Cite this