A speaker identification system using a model of artificial neural networks for an elevator application

被引：14

作者：

Adami, AG

Barone, DAC

机构：

[1] Univ Caxias Do Sul, Dept Informat, BR-95070560 Caxias Do Sul, RS, Brazil

[2] Univ Fed Rio Grande Sul, Inst Informat, BR-91000000 Porto Alegre, RS, Brazil

来源：

INFORMATION SCIENCES | 2001年 / 138卷 / 1-4期

关键词：

Elevators - Mathematical models - Multilayer neural networks - Pattern recognition systems - Security systems - Speech analysis - Speech coding;

D O I：

10.1016/S0020-0255(01)00129-3

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a comparison of some features for speaker identification applied to a building security system. The features used in this paper are pitch, frequency formants, linear predictive coding (LPC) coefficients and cepstral coefficients computed from LPC. The comparison was based on a system for building security that uses the voice of the residents to control the access to the building. The system uses a model of artificial neural network called multi-layer perceptron (MLP) as a classifier. This paper shows that cepstral coefficients are more efficient than LPC coefficients for the security system. (C) 2001 Elsevier Science Inc. All rights reserved.

引用

页码：1 / 5

页数：5