Multi-resolution form of SVD for text-independent speaker recognition

被引：15

作者：

Lung, SY ^{[1
]}

机构：

[1] Chung Kuo Inst Technol, Dept Management Informat Syst, Taipei, Taiwan

来源：

PATTERN RECOGNITION | 2002年 / 35卷 / 07期

关键词：

speaker recognition; singular value decomposition; Karhunen-Loeve transform;

D O I：

10.1016/S0031-3203(02)00015-8

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A text-independent speaker recognition system based on multi-resolution singular value decomposition (MSVD) is proposed. The MSVD is applied to the speaker data compression and feature extraction not at the square matrix, Our results have shown that this MSVD introduced better performance than the other Karhunen-Loeve transform with respect to the percentages of recognition. (C) 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

引用

页码：1637 / 1639

页数：3

共 4 条

[1] Hard-limited Karhunen-Loeve transform for text independent speaker recognition [J].

Chen, CCT ;

Chen, CT ;

Tsai, CM .

ELECTRONICS LETTERS, 1997, 33 (24) :2014-2016

[2] Further reduced form of Karhunen-Loeve transform for text independent speaker recognition [J].

Lung, SY ;

Chen, CCT .

ELECTRONICS LETTERS, 1998, 34 (14) :1380-1382

[3] Disk distance measure of speaker recognition [J].

Lung, SY .

ELECTRONICS LETTERS, 1997, 33 (20) :1678-1679

[4] A new approach for text-independent speaker recognition [J].

Lung, SY ;

Chen, CCT .

PATTERN RECOGNITION, 2000, 33 (08) :1401-1403

← 1 →