Feature selection for a DTW-based speaker verification system

被引：0

作者：

Pandit, M ^{[1
]}

Kittler, J ^{[1
]}

机构：

[1] Univ Surrey, Sch Elect Engn Informat Technol & Math, Ctr Vis Speech & Signal Proc, Guildford GU2 5XH, Surrey, England

来源：

PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6 | 1998年

关键词：

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Speaker verification systems, in general, require 20 to 30 features as input for satisfactory verification. We show that this feature set can be optimised by appropriately choosing proper feature subset from the input feature set. This paper proposes a technique for optimisation of the feature sets, in an Dynamic Time Warping (DTW) based text-dependent speaker verification system, to improve false acceptance rate. The optimisation technique is based on the 1-r algorithm.The proposed scheme is applied to study cepstrum coefficients and their first order orthogonal polynomial coefficients. Experiments are conducted on two data bases: French and Spanish. The results indicate that with the optimised feature set the performance of the system may improve but it is never degraded. Moreover, the speed of verification is significantly increased.

引用

页码：769 / 772

页数：4