Driver voice identification system using auto-correlation function and average magnitude difference function

Jian-Da Wu, Pang Yi Liu, Guan Long Hong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study presents a driver identification system using voice analysis for a vehicle security system. The structure of the proposed system has three parts. The first procedure is speech pre-processing, the second is feature extraction of sound signals, and the third is classification of driver voice. Initially, a database of sound signals for several drivers was established. The volume and zero-crossing rate (ZCR) of sound are used to detect the voice end-point in order to reduce data computation. Then the Auto-correlation Function (ACF) and Average Magnitude Difference Function (AMDF) methods are applied to retrieve the voice pitch features. Finally these features are used to identify the drivers by a General Regression Neural Network (GRNN). The experimental results show that the development of this voice identification system can use fewer feature vectors of pitch to obtain a good recognition rate.

Original languageEnglish
Title of host publicationMechanical Design and Power Engineering
Pages1287-1292
Number of pages6
DOIs
Publication statusPublished - 2014 Feb 20
Event2013 2nd International Conference on Mechanical Design and Power Engineering, ICMDPE 2013 - Beijing, China
Duration: 2013 Nov 292013 Nov 30

Publication series

NameApplied Mechanics and Materials
Volume490-491
ISSN (Print)1660-9336
ISSN (Electronic)1662-7482

Conference

Conference2013 2nd International Conference on Mechanical Design and Power Engineering, ICMDPE 2013
CountryChina
CityBeijing
Period13-11-2913-11-30

Fingerprint

Autocorrelation
Identification (control systems)
Acoustic waves
Security systems
Feature extraction
Neural networks
Processing

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Wu, J-D., Liu, P. Y., & Hong, G. L. (2014). Driver voice identification system using auto-correlation function and average magnitude difference function. In Mechanical Design and Power Engineering (pp. 1287-1292). (Applied Mechanics and Materials; Vol. 490-491). https://doi.org/10.4028/www.scientific.net/AMM.490-491.1287
Wu, Jian-Da ; Liu, Pang Yi ; Hong, Guan Long. / Driver voice identification system using auto-correlation function and average magnitude difference function. Mechanical Design and Power Engineering. 2014. pp. 1287-1292 (Applied Mechanics and Materials).
@inproceedings{cc419b7c4a884e689f11b7ed1a33f2f0,
title = "Driver voice identification system using auto-correlation function and average magnitude difference function",
abstract = "This study presents a driver identification system using voice analysis for a vehicle security system. The structure of the proposed system has three parts. The first procedure is speech pre-processing, the second is feature extraction of sound signals, and the third is classification of driver voice. Initially, a database of sound signals for several drivers was established. The volume and zero-crossing rate (ZCR) of sound are used to detect the voice end-point in order to reduce data computation. Then the Auto-correlation Function (ACF) and Average Magnitude Difference Function (AMDF) methods are applied to retrieve the voice pitch features. Finally these features are used to identify the drivers by a General Regression Neural Network (GRNN). The experimental results show that the development of this voice identification system can use fewer feature vectors of pitch to obtain a good recognition rate.",
author = "Jian-Da Wu and Liu, {Pang Yi} and Hong, {Guan Long}",
year = "2014",
month = "2",
day = "20",
doi = "10.4028/www.scientific.net/AMM.490-491.1287",
language = "English",
isbn = "9783038350019",
series = "Applied Mechanics and Materials",
pages = "1287--1292",
booktitle = "Mechanical Design and Power Engineering",

}

Wu, J-D, Liu, PY & Hong, GL 2014, Driver voice identification system using auto-correlation function and average magnitude difference function. in Mechanical Design and Power Engineering. Applied Mechanics and Materials, vol. 490-491, pp. 1287-1292, 2013 2nd International Conference on Mechanical Design and Power Engineering, ICMDPE 2013, Beijing, China, 13-11-29. https://doi.org/10.4028/www.scientific.net/AMM.490-491.1287

Driver voice identification system using auto-correlation function and average magnitude difference function. / Wu, Jian-Da; Liu, Pang Yi; Hong, Guan Long.

Mechanical Design and Power Engineering. 2014. p. 1287-1292 (Applied Mechanics and Materials; Vol. 490-491).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Driver voice identification system using auto-correlation function and average magnitude difference function

AU - Wu, Jian-Da

AU - Liu, Pang Yi

AU - Hong, Guan Long

PY - 2014/2/20

Y1 - 2014/2/20

N2 - This study presents a driver identification system using voice analysis for a vehicle security system. The structure of the proposed system has three parts. The first procedure is speech pre-processing, the second is feature extraction of sound signals, and the third is classification of driver voice. Initially, a database of sound signals for several drivers was established. The volume and zero-crossing rate (ZCR) of sound are used to detect the voice end-point in order to reduce data computation. Then the Auto-correlation Function (ACF) and Average Magnitude Difference Function (AMDF) methods are applied to retrieve the voice pitch features. Finally these features are used to identify the drivers by a General Regression Neural Network (GRNN). The experimental results show that the development of this voice identification system can use fewer feature vectors of pitch to obtain a good recognition rate.

AB - This study presents a driver identification system using voice analysis for a vehicle security system. The structure of the proposed system has three parts. The first procedure is speech pre-processing, the second is feature extraction of sound signals, and the third is classification of driver voice. Initially, a database of sound signals for several drivers was established. The volume and zero-crossing rate (ZCR) of sound are used to detect the voice end-point in order to reduce data computation. Then the Auto-correlation Function (ACF) and Average Magnitude Difference Function (AMDF) methods are applied to retrieve the voice pitch features. Finally these features are used to identify the drivers by a General Regression Neural Network (GRNN). The experimental results show that the development of this voice identification system can use fewer feature vectors of pitch to obtain a good recognition rate.

UR - http://www.scopus.com/inward/record.url?scp=84893944197&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893944197&partnerID=8YFLogxK

U2 - 10.4028/www.scientific.net/AMM.490-491.1287

DO - 10.4028/www.scientific.net/AMM.490-491.1287

M3 - Conference contribution

AN - SCOPUS:84893944197

SN - 9783038350019

T3 - Applied Mechanics and Materials

SP - 1287

EP - 1292

BT - Mechanical Design and Power Engineering

ER -

Wu J-D, Liu PY, Hong GL. Driver voice identification system using auto-correlation function and average magnitude difference function. In Mechanical Design and Power Engineering. 2014. p. 1287-1292. (Applied Mechanics and Materials). https://doi.org/10.4028/www.scientific.net/AMM.490-491.1287