NEURAL NETWORK ADAPTIVE WAVELETS FOR SIGNAL REPRESENTATION AND CLASSIFICATION

被引：226

作者：

SZU, HH ^{[1
]}

TELFER, B ^{[1
]}

KADAMBE, S ^{[1
]}

机构：

[1] ALFRED I DUPONT INST,APPL SCI & ENGN LABS,WILMINGTON,DE 19899

来源：

OPTICAL ENGINEERING | 1992年 / 31卷 / 09期

关键词：

WAVELET TRANSFORMS; CLASSIFICATION; FEATURE SELECTION; NEURAL NETWORKS; PHONEME RECOGNITION; SIGNAL APPROXIMATION; SIGNAL REPRESENTATION; SPEAKER RECOGNITION;

D O I：

10.1117/12.59918

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

Methods are presented for adaptively generating wavelet templates for signal representation and classification using neural networks. Different network structures and energy functions are necessary and are given for representation and classification. The idea is introduced of a "super-wavelet," a linear combination of wavelets that itself is treated as a wavelet. The super-wavelet allows the shape of the wavelet to adapt to a particular problem, which goes beyond adapting parameters of a fixed-shape wavelet. Simulations are given for 1-D signals, with the concepts extendable to imagery. Ideas are discussed for applying the concepts in the paper to phoneme and speaker recognition.

引用

页码：1907 / 1916

页数：10

共 32 条

[1]

Broomhead D. S., 1988, Complex Systems, V2, P321

[2]

CASASENT D, 1992, P SPIE APR, V1702

[3] ENTROPY-BASED ALGORITHMS FOR BEST BASIS SELECTION [J].

COIFMAN, RR ;

WICKERHAUSER, MV .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1992, 38 (02) :713-718

[4] COMPLETE DISCRETE 2-D GABOR TRANSFORMS BY NEURAL NETWORKS FOR IMAGE-ANALYSIS AND COMPRESSION [J].

DAUGMAN, JG .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (07) :1169-1179

[5] IMAGE COMPRESSION THROUGH WAVELET TRANSFORM CODING [J].

DEVORE, RA ;

JAWERTH, B ;

LUCIER, BJ .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1992, 38 (02) :719-746

[6] SPEAKER RECOGNITION - IDENTIFYING PEOPLE BY THEIR VOICES [J].

DODDINGTON, GR .

PROCEEDINGS OF THE IEEE, 1985, 73 (11) :1651-1664

[7]

Duda R. O., 1973, PATTERN CLASSIFICATI, V3

[8]

Flanagan JL, 2013, SPEECH ANAL SYNTHESI

[9]

Fletcher R., 1987, PRACTICAL METHODS OP

[10] SPEAKER-IDENTIFYING FEATURES BASED ON FORMANT TRACKS [J].

GOLDSTEIN, UG .

JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1976, 59 (01) :176-182

← 1 2 3 4 →