Committees of RBFN - A novel connectionist model for speech recognition

S. Meenakshisundaram; W. L. Woo; S. S. Dlay

Committees of RBFN - A novel connectionist model for speech recognition

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

^*Corresponding author for this work

Computer and Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-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 language	English
Title of host publication	Proceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing
Editors	A.P. Pobil
Publisher	ACTA Press
Pages	300-304
Number of pages	5
ISBN (Print)	0889864586
Publication status	Published - 27 Dec 2004
Event	Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing - Marbella, Spain Duration: 1 Sep 2004 → 3 Sep 2004

Conference

Conference	Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing
Country/Territory	Spain
City	Marbella
Period	1/09/04 → 3/09/04

Cite this

@inproceedings{a74b880ea9ae47f9b66894556efb14a2,

title = "Committees of RBFN - A novel connectionist model for speech recognition",

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.",

keywords = "Committee Machines and Radial Basis Functions, Hybrid Connectionist",

author = "S. Meenakshisundaram and Woo, {W. L.} and Dlay, {S. S.}",

year = "2004",

month = dec,

day = "27",

language = "English",

isbn = "0889864586",

pages = "300--304",

editor = "A.P. Pobil",

booktitle = "Proceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing",

publisher = "ACTA Press",

address = "Canada",

note = "Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing ; Conference date: 01-09-2004 Through 03-09-2004",

}

Meenakshisundaram, S, Woo, WL & Dlay, SS 2004, Committees of RBFN - A novel connectionist model for speech recognition. in AP Pobil (ed.), Proceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing. ACTA Press, pp. 300-304, Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing, Marbella, Spain, 1/09/04.

Committees of RBFN - A novel connectionist model for speech recognition. / Meenakshisundaram, S.; Woo, W. L.; Dlay, S. S.

Proceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing. ed. / A.P. Pobil. ACTA Press, 2004. p. 300-304.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Committees of RBFN - A novel connectionist model for speech recognition

AU - Meenakshisundaram, S.

AU - Woo, W. L.

AU - Dlay, S. S.

PY - 2004/12/27

Y1 - 2004/12/27

N2 - 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.

AB - 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.

KW - Committee Machines and Radial Basis Functions

KW - Hybrid Connectionist

M3 - Conference contribution

AN - SCOPUS:10444236466

SN - 0889864586

SP - 300

EP - 304

BT - Proceedings of the Eighth IASTED International Conference On Artificial Intelligence and Soft Computing

A2 - Pobil, A.P.

PB - ACTA Press

T2 - Proceedings of the Eighth IASTED International Conference on Atificial Intelligence and Soft Computing

Y2 - 1 September 2004 through 3 September 2004

ER -

Committees of RBFN - A novel connectionist model for speech recognition

Abstract

Conference

Fingerprint

Cite this