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

facebooktwittermailshare

ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION

Abstract: 

An attacker may use a variety of techniques to fool an automatic speaker verification system into accepting them as a genuine user. Anti-spoofing methods meanwhile aim to make the system robust against such attacks. The ASVspoof 2017 Challenge focused specifically on replay attacks, with the intention of measuring the limits of replay attack detection as well as developing countermeasures against them. In this work, we propose our replay attacks detection system - Attentive Filtering Network, which is composed of an attention-based filtering mechanism that enhances feature representations in both the frequency and time domains, and a ResNet-based classifier. We show that the network enables us to visualize the automatically acquired feature representations that are helpful for spoofing detection. Attentive Filtering Network attains an evaluation EER of 8.99% on the ASVspoof 2017 Version 2.0 dataset. With system fusion, our best system further obtains a 30% relative improvement over the ASVspoof 2017 enhanced baseline system.

up
0 users have voted:

Paper Details

Authors:
Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King
Submitted On:
9 May 2019 - 3:24pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Cheng-I Lai
Document Year:
2019
Cite

Document Files

ICASSP poster (1).pdf

(35)

Subscribe

[1] Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King, "ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4233. Accessed: Nov. 20, 2019.
@article{4233-19,
url = {http://sigport.org/4233},
author = {Cheng-I Lai; Alberto Abad; Korin Richmond; Junichi Yamagishi; Najim Dehak; Simon King },
publisher = {IEEE SigPort},
title = {ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION},
year = {2019} }
TY - EJOUR
T1 - ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION
AU - Cheng-I Lai; Alberto Abad; Korin Richmond; Junichi Yamagishi; Najim Dehak; Simon King
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4233
ER -
Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King. (2019). ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION. IEEE SigPort. http://sigport.org/4233
Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King, 2019. ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION. Available at: http://sigport.org/4233.
Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King. (2019). "ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION." Web.
1. Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King. ATTENTIVE FILTERING NETWORKS FOR AUDIO REPLAY ATTACK DETECTION [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4233