Two level cluster analysis based on fractal dimension and iterated function systems (IFS) for speech signal recognition

被引：8

作者：

Bohez, ELJ ^{[1
]}

机构：

[1] Asian Inst Technol, Bangkok 10501, Thailand

来源：

APCCAS '98 - IEEE ASIA-PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS: MICROELECTRONICS AND INTEGRATING SYSTEMS | 1998年

关键词：

D O I：

10.1109/APCCAS.1998.743749

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

A phoneme recognition method is presented based on Fractal theory. Fractal Dimension and IFS (Iterated Function System) parameters that represent the Methods to calculate the Fractal Dimension are investigated for word segmentation. The IFS matrices and the eigenvalues of the covariance matrix are proposed for phoneme recognition.

引用

页码：291 / 294

页数：4

共 4 条

[1] FRACTAL DIMENSION AND ITERATED FUNCTION SYSTEM (IFS) FOR SPEECH RECOGNITION [J].

BOHEZ, ELJ ;

SENEVIRATHNE, TR ;

VANWINDEN, JA .

ELECTRONICS LETTERS, 1992, 28 (15) :1382-1384

[2] SPEAKER-INDEPENDENT RECOGNITION OF ISOLATED WORDS USING CLUSTERING TECHNIQUES [J].

RABINER, LR ;

LEVINSON, SE ;

ROSENBERG, AE ;

WILPON, JG .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1979, 27 (04) :336-349

[3]

Rousseeuw P.J., 1990, Finding groups in data: An introduction to cluster analysis, V1

[4] AMPLITUDE SCALE METHOD - NEW AND EFFICIENT APPROACH TO MEASURE FRACTAL DIMENSION OF SPEECH WAVE-FORMS [J].

SENEVIRATHNE, TR ;

BOHEZ, ELJ ;

VANWINDEN, JA .

ELECTRONICS LETTERS, 1992, 28 (04) :420-422

← 1 →