The fusion of forensic speaker verification systems

Huapeng Wang; Jun Yang

doi:10.1109/CISP.2011.6100731

The fusion of forensic speaker verification systems

Huapeng Wang^*, Jun Yang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

The discriminant performance of fused forensic speaker verification systems in likelihood ratios framework was tested. Likelihood ratios were calculated using a multivariate kernel-density (MVKD) approach and the parameters used in this paper are LPC,LPCC and MFCC extracted from the Chinese vowel /a/ in the telephone recordings database, and the reliability of the fused forensic speaker verification systems was measured using the log-likelihood-ratio-cost function.

Original language	English
Title of host publication	Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Pages	2450-2453
Number of pages	4
DOIs	https://doi.org/10.1109/CISP.2011.6100731
Publication status	Published - 2011
Externally published	Yes
Event	4th International Congress on Image and Signal Processing, CISP 2011 - Shanghai, China Duration: Oct 15 2011 → Oct 17 2011

Publication series

Name	Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011
Volume	5

Conference

Conference	4th International Congress on Image and Signal Processing, CISP 2011
Country/Territory	China
City	Shanghai
Period	10/15/11 → 10/17/11

ASJC Scopus Subject Areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Signal Processing

Keywords

forensic speaker verification system
fusion
likelihood ratio
multivariate kernel-density

Access to Document

10.1109/CISP.2011.6100731

Cite this

@inproceedings{7a35ced79d6f4799913763ccc7ed7487,

title = "The fusion of forensic speaker verification systems",

abstract = "The discriminant performance of fused forensic speaker verification systems in likelihood ratios framework was tested. Likelihood ratios were calculated using a multivariate kernel-density (MVKD) approach and the parameters used in this paper are LPC,LPCC and MFCC extracted from the Chinese vowel /a/ in the telephone recordings database, and the reliability of the fused forensic speaker verification systems was measured using the log-likelihood-ratio-cost function.",

keywords = "forensic speaker verification system, fusion, likelihood ratio, multivariate kernel-density",

author = "Huapeng Wang and Jun Yang",

year = "2011",

doi = "10.1109/CISP.2011.6100731",

language = "English",

isbn = "9781424493067",

series = "Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011",

pages = "2450--2453",

booktitle = "Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011",

note = "4th International Congress on Image and Signal Processing, CISP 2011 ; Conference date: 15-10-2011 Through 17-10-2011",

}

Wang, H & Yang, J 2011, The fusion of forensic speaker verification systems. in Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011., 6100731, Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011, vol. 5, pp. 2450-2453, 4th International Congress on Image and Signal Processing, CISP 2011, Shanghai, China, 10/15/11. https://doi.org/10.1109/CISP.2011.6100731

The fusion of forensic speaker verification systems. / Wang, Huapeng; Yang, Jun.
Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011. 2011. p. 2450-2453 6100731 (Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011; Vol. 5).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - The fusion of forensic speaker verification systems

AU - Wang, Huapeng

AU - Yang, Jun

PY - 2011

Y1 - 2011

N2 - The discriminant performance of fused forensic speaker verification systems in likelihood ratios framework was tested. Likelihood ratios were calculated using a multivariate kernel-density (MVKD) approach and the parameters used in this paper are LPC,LPCC and MFCC extracted from the Chinese vowel /a/ in the telephone recordings database, and the reliability of the fused forensic speaker verification systems was measured using the log-likelihood-ratio-cost function.

AB - The discriminant performance of fused forensic speaker verification systems in likelihood ratios framework was tested. Likelihood ratios were calculated using a multivariate kernel-density (MVKD) approach and the parameters used in this paper are LPC,LPCC and MFCC extracted from the Chinese vowel /a/ in the telephone recordings database, and the reliability of the fused forensic speaker verification systems was measured using the log-likelihood-ratio-cost function.

KW - forensic speaker verification system

KW - fusion

KW - likelihood ratio

KW - multivariate kernel-density

UR - http://www.scopus.com/inward/record.url?scp=84862927931&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862927931&partnerID=8YFLogxK

U2 - 10.1109/CISP.2011.6100731

DO - 10.1109/CISP.2011.6100731

M3 - Conference contribution

AN - SCOPUS:84862927931

SN - 9781424493067

T3 - Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011

SP - 2450

EP - 2453

BT - Proceedings - 4th International Congress on Image and Signal Processing, CISP 2011

T2 - 4th International Congress on Image and Signal Processing, CISP 2011

Y2 - 15 October 2011 through 17 October 2011

ER -

The fusion of forensic speaker verification systems

Abstract

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this