Connectionist fuzzy classifier for speech recognition

Yau Hwang Kuo, Cheng I. Kao, Jiahn Jung Chen

Research output: Contribution to journalArticle

Abstract

A neural network model based on the fuzzy classification concept, called the Connectionist Fuzzy Classifier (CFC), is proposed. The CFC model originates from embedding a 'weighted Euclidean distance' fuzzy classification procedure into a four-layered neural network architecture. It employs a one-pass learning algorithm, which can overcome the two major drawbacks of the backpropagation model: the local minimum problem and long training time. Some experiments and comparisons between CFC and some different neural network models are made in this paper. The experimental results show that the CFC model has better accuracy for speech recognition than do the PNN, backpropagation, and linear matching methods, especially in a noisy environment.

Original languageEnglish
Pages (from-to)1-20
Number of pages20
JournalJournal of Information Science and Engineering
Volume10
Issue number1
Publication statusPublished - 1994 Mar 1

Fingerprint

Speech recognition
Classifiers
neural network
Neural networks
Backpropagation
Network architecture
Learning algorithms
experiment
learning
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Library and Information Sciences
  • Computational Theory and Mathematics

Cite this

Kuo, Yau Hwang ; Kao, Cheng I. ; Chen, Jiahn Jung. / Connectionist fuzzy classifier for speech recognition. In: Journal of Information Science and Engineering. 1994 ; Vol. 10, No. 1. pp. 1-20.
@article{85c7473f27864056972f087701c6ff95,
title = "Connectionist fuzzy classifier for speech recognition",
abstract = "A neural network model based on the fuzzy classification concept, called the Connectionist Fuzzy Classifier (CFC), is proposed. The CFC model originates from embedding a 'weighted Euclidean distance' fuzzy classification procedure into a four-layered neural network architecture. It employs a one-pass learning algorithm, which can overcome the two major drawbacks of the backpropagation model: the local minimum problem and long training time. Some experiments and comparisons between CFC and some different neural network models are made in this paper. The experimental results show that the CFC model has better accuracy for speech recognition than do the PNN, backpropagation, and linear matching methods, especially in a noisy environment.",
author = "Kuo, {Yau Hwang} and Kao, {Cheng I.} and Chen, {Jiahn Jung}",
year = "1994",
month = "3",
day = "1",
language = "English",
volume = "10",
pages = "1--20",
journal = "Journal of Information Science and Engineering",
issn = "1016-2364",
publisher = "Institute of Information Science",
number = "1",

}

Connectionist fuzzy classifier for speech recognition. / Kuo, Yau Hwang; Kao, Cheng I.; Chen, Jiahn Jung.

In: Journal of Information Science and Engineering, Vol. 10, No. 1, 01.03.1994, p. 1-20.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Connectionist fuzzy classifier for speech recognition

AU - Kuo, Yau Hwang

AU - Kao, Cheng I.

AU - Chen, Jiahn Jung

PY - 1994/3/1

Y1 - 1994/3/1

N2 - A neural network model based on the fuzzy classification concept, called the Connectionist Fuzzy Classifier (CFC), is proposed. The CFC model originates from embedding a 'weighted Euclidean distance' fuzzy classification procedure into a four-layered neural network architecture. It employs a one-pass learning algorithm, which can overcome the two major drawbacks of the backpropagation model: the local minimum problem and long training time. Some experiments and comparisons between CFC and some different neural network models are made in this paper. The experimental results show that the CFC model has better accuracy for speech recognition than do the PNN, backpropagation, and linear matching methods, especially in a noisy environment.

AB - A neural network model based on the fuzzy classification concept, called the Connectionist Fuzzy Classifier (CFC), is proposed. The CFC model originates from embedding a 'weighted Euclidean distance' fuzzy classification procedure into a four-layered neural network architecture. It employs a one-pass learning algorithm, which can overcome the two major drawbacks of the backpropagation model: the local minimum problem and long training time. Some experiments and comparisons between CFC and some different neural network models are made in this paper. The experimental results show that the CFC model has better accuracy for speech recognition than do the PNN, backpropagation, and linear matching methods, especially in a noisy environment.

UR - http://www.scopus.com/inward/record.url?scp=0028402977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028402977&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0028402977

VL - 10

SP - 1

EP - 20

JO - Journal of Information Science and Engineering

JF - Journal of Information Science and Engineering

SN - 1016-2364

IS - 1

ER -