Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A new approach for robust replay spoof detection in ASV systems

Abstract: 

The objective of this paper is to extract robust features for
detecting replay spoof attacks on text-independent speaker
verification systems. In the case of replay attacks, prere-
corded utterance of the target speaker is played to the auto-
matic speaker verification system (ASV)to gain unauthorized
access. In such a scenario, the speech signal carries the char-
acteristics of the intermediate recording device as well. In the
proposed approach, the characteristics of the intermediate de-
vice are highlighted by subtracting the contribution of the live
speech in the cepstral domain. An overcomplete dictionary
learned on cepstral features extracted from live speech data,
is used to subtract the contribution of live speech. The resid-
ual captures the characteristics of recording device, and can
be used to distinguish spoof speech signal from live speech
signal. The distribution of the residuals from live and spoof
speech signals are captured using Gaussian mixture models
(GMMs). The likelihood ratio computed from the GMMs
built on spoof and live signals, respectively, is used to de-
tect the spoof attack. The performance of the proposed ap-
proach is evaluated on ASVspoof 2017 evaluation challenge
database. The proposed feature extraction method achieved
11% relative improvement over the base line system built on
the constant-Q cepstral coefficients.

up
0 users have voted:

Paper Details

Authors:
B Shaik Mohammad Rafi
Submitted On:
11 November 2017 - 8:08am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Shekhar Nayak
Paper Code:
1547
Document Year:
2017
Cite

Document Files

A new approach for robust replay spoof detection in ASV systems.pdf

(84 downloads)

Subscribe

[1] B Shaik Mohammad Rafi, "A new approach for robust replay spoof detection in ASV systems", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2306. Accessed: Jul. 17, 2018.
@article{2306-17,
url = {http://sigport.org/2306},
author = {B Shaik Mohammad Rafi },
publisher = {IEEE SigPort},
title = {A new approach for robust replay spoof detection in ASV systems},
year = {2017} }
TY - EJOUR
T1 - A new approach for robust replay spoof detection in ASV systems
AU - B Shaik Mohammad Rafi
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2306
ER -
B Shaik Mohammad Rafi. (2017). A new approach for robust replay spoof detection in ASV systems. IEEE SigPort. http://sigport.org/2306
B Shaik Mohammad Rafi, 2017. A new approach for robust replay spoof detection in ASV systems. Available at: http://sigport.org/2306.
B Shaik Mohammad Rafi. (2017). "A new approach for robust replay spoof detection in ASV systems." Web.
1. B Shaik Mohammad Rafi. A new approach for robust replay spoof detection in ASV systems [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2306