A cascaded voice biometric system

Roaya Salhalden A. Abdalrahman; Bülent Bolat; Nihan Kahraman

doi:10.1016/j.procs.2018.04.334

A cascaded voice biometric system

Roaya Salhalden A. Abdalrahman
, Bülent Bolat^*
, Nihan Kahraman

^*Corresponding author for this work

Yildiz Technical University

Research output: Contribution to journal › Conference article › peer-review

2 Citations (Scopus)

Abstract

This paper presents a voice biometric system which uses both text dependent and independent speaker and speech recognition methods. The Mel Frequency Cepstral Coefficients (MFCC) and pitch period are used as features and the decision is made by using Euclidian distance metric. This cascaded procedure reduces the False Positive Rate and increases the security of biometric recognition system. It is shown that cascaded system defines voice recognition better in terms of accuracy, safety and difficulty of penetration. The efficiency of the identification system is high up to approximately 91.2%.

Original language	English
Pages (from-to)	1223-1228
Number of pages	6
Journal	Procedia Computer Science
Volume	131
DOIs	https://doi.org/10.1016/j.procs.2018.04.334
Publication status	Published - 2018
Externally published	Yes
Event	8th International Congress of Information and Communication Technology, ICICT 2018 - Xiamen, China Duration: 27 Jan 2018 → 28 Jan 2018

Bibliographical note

Publisher Copyright:
© 2018 The Authors. Published by Elsevier Ltd.

Keywords

Mel frequency cepstral coefficients
Pitch period
Speaker recognition

Access to Document

10.1016/j.procs.2018.04.334

Cite this

@article{6137db76f973434bb925321dafda9c34,

title = "A cascaded voice biometric system",

abstract = "This paper presents a voice biometric system which uses both text dependent and independent speaker and speech recognition methods. The Mel Frequency Cepstral Coefficients (MFCC) and pitch period are used as features and the decision is made by using Euclidian distance metric. This cascaded procedure reduces the False Positive Rate and increases the security of biometric recognition system. It is shown that cascaded system defines voice recognition better in terms of accuracy, safety and difficulty of penetration. The efficiency of the identification system is high up to approximately 91.2\%.",

keywords = "Mel frequency cepstral coefficients, Pitch period, Speaker recognition",

author = "Abdalrahman, \{Roaya Salhalden A.\} and B{\"u}lent Bolat and Nihan Kahraman",

note = "Publisher Copyright: {\textcopyright} 2018 The Authors. Published by Elsevier Ltd.; 8th International Congress of Information and Communication Technology, ICICT 2018 ; Conference date: 27-01-2018 Through 28-01-2018",

year = "2018",

doi = "10.1016/j.procs.2018.04.334",

language = "English",

volume = "131",

pages = "1223--1228",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - A cascaded voice biometric system

AU - Abdalrahman, Roaya Salhalden A.

AU - Bolat, Bülent

AU - Kahraman, Nihan

PY - 2018

Y1 - 2018

N2 - This paper presents a voice biometric system which uses both text dependent and independent speaker and speech recognition methods. The Mel Frequency Cepstral Coefficients (MFCC) and pitch period are used as features and the decision is made by using Euclidian distance metric. This cascaded procedure reduces the False Positive Rate and increases the security of biometric recognition system. It is shown that cascaded system defines voice recognition better in terms of accuracy, safety and difficulty of penetration. The efficiency of the identification system is high up to approximately 91.2%.

AB - This paper presents a voice biometric system which uses both text dependent and independent speaker and speech recognition methods. The Mel Frequency Cepstral Coefficients (MFCC) and pitch period are used as features and the decision is made by using Euclidian distance metric. This cascaded procedure reduces the False Positive Rate and increases the security of biometric recognition system. It is shown that cascaded system defines voice recognition better in terms of accuracy, safety and difficulty of penetration. The efficiency of the identification system is high up to approximately 91.2%.

KW - Mel frequency cepstral coefficients

KW - Pitch period

KW - Speaker recognition

UR - https://www.scopus.com/pages/publications/85061297428

U2 - 10.1016/j.procs.2018.04.334

DO - 10.1016/j.procs.2018.04.334

M3 - Conference article

AN - SCOPUS:85061297428

SN - 1877-0509

VL - 131

SP - 1223

EP - 1228

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 8th International Congress of Information and Communication Technology, ICICT 2018

Y2 - 27 January 2018 through 28 January 2018

ER -

A cascaded voice biometric system

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this