Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition

K. F. Leung; Hung Fat Frank Leung; H. K. Lam; S. H. Ling

doi:10.1007/s00521-006-0068-4

Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition

K. F. Leung, Hung Fat Frank Leung, H. K. Lam, S. H. Ling

Research output: Journal article publication › Journal article › Academic research › peer-review

20 Citations (Scopus)

Abstract

This paper presents the recognition of speech commands using a modified neural fuzzy network (NFN). By introducing associative memory (the tuner NFN) into the classification process (the classifier NFN), the network parameters could be made adaptive to changing input data. Then, the search space of the classification network could be enlarged by a single network. To train the parameters of the modified NFN, an improved genetic algorithm is proposed. As an application example, the proposed speech recognition approach is implemented in an eBook experimentally to illustrate the design and its merits.

Original language	English
Pages (from-to)	419-431
Number of pages	13
Journal	Neural Computing and Applications
Volume	16
Issue number	4-5
DOIs	https://doi.org/10.1007/s00521-006-0068-4
Publication status	Published - 1 May 2007

Keywords

Fuzzy logic
Genetic algorithm
Neural network
Pattern recognition
Speech recognition

ASJC Scopus subject areas

Control and Systems Engineering
Artificial Intelligence

More information

10.1007/s00521-006-0068-4

Cite this

@article{b048885b38ac4e52a21894a0811aac38,

title = "Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition",

abstract = "This paper presents the recognition of speech commands using a modified neural fuzzy network (NFN). By introducing associative memory (the tuner NFN) into the classification process (the classifier NFN), the network parameters could be made adaptive to changing input data. Then, the search space of the classification network could be enlarged by a single network. To train the parameters of the modified NFN, an improved genetic algorithm is proposed. As an application example, the proposed speech recognition approach is implemented in an eBook experimentally to illustrate the design and its merits.",

keywords = "Fuzzy logic, Genetic algorithm, Neural network, Pattern recognition, Speech recognition",

author = "Leung, {K. F.} and Leung, {Hung Fat Frank} and Lam, {H. K.} and Ling, {S. H.}",

year = "2007",

month = may,

day = "1",

doi = "10.1007/s00521-006-0068-4",

language = "English",

volume = "16",

pages = "419--431",

journal = "Neural Computing and Applications",

issn = "0941-0643",

publisher = "Springer London",

number = "4-5",

}

TY - JOUR

T1 - Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition

AU - Leung, K. F.

AU - Leung, Hung Fat Frank

AU - Lam, H. K.

AU - Ling, S. H.

PY - 2007/5/1

Y1 - 2007/5/1

N2 - This paper presents the recognition of speech commands using a modified neural fuzzy network (NFN). By introducing associative memory (the tuner NFN) into the classification process (the classifier NFN), the network parameters could be made adaptive to changing input data. Then, the search space of the classification network could be enlarged by a single network. To train the parameters of the modified NFN, an improved genetic algorithm is proposed. As an application example, the proposed speech recognition approach is implemented in an eBook experimentally to illustrate the design and its merits.

AB - This paper presents the recognition of speech commands using a modified neural fuzzy network (NFN). By introducing associative memory (the tuner NFN) into the classification process (the classifier NFN), the network parameters could be made adaptive to changing input data. Then, the search space of the classification network could be enlarged by a single network. To train the parameters of the modified NFN, an improved genetic algorithm is proposed. As an application example, the proposed speech recognition approach is implemented in an eBook experimentally to illustrate the design and its merits.

KW - Fuzzy logic

KW - Genetic algorithm

KW - Neural network

KW - Pattern recognition

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=34249026341&partnerID=8YFLogxK

U2 - 10.1007/s00521-006-0068-4

DO - 10.1007/s00521-006-0068-4

M3 - Journal article

SN - 0941-0643

VL - 16

SP - 419

EP - 431

JO - Neural Computing and Applications

JF - Neural Computing and Applications

IS - 4-5

ER -

Application of a modified neural fuzzy network and an improved genetic algorithm to speech recognition

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this