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

facebooktwittermailshare

End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks

Abstract: 

In this contribution, we introduce convolutional neural network architectures aiming at performing end-to-end detection of attacks to voice biometrics systems, i.e. the model provides scores corresponding to the likelihood of attack given general purpose time-frequency features obtained from speech. Microphone level attackers based on speech synthesis and voice conversion techniques are considered, along with presentation replay attacks. While the convolutional models yield a sequence of representations corresponding to different parts of the input at varying time steps, concatenated first- and second-order statistics pooled from the outputs of a self-attention layer are used as a fixed-dimension representations of utterances of varying length, which are then input into a set of fully connected layers to finally yield scores. Evaluation of the proposed framework is performed with data from ASVspoof 2019 challenge yielding relative improvements higher than one order of magnitude in terms of equal error rate over two baseline systems provided by ASVspoof 2019's organizers, and significant improvements over the benchmark systems we evaluated.

up
0 users have voted:

Paper Details

Authors:
Joao Monteiro,Jahangir Alam,Tiago H. Falk
Submitted On:
6 November 2019 - 2:12pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Joao Monteiro
Paper Code:
204
Document Year:
2019
Cite

Document Files

MLSP_E2E_SpoofingDetection.pdf

(2)

Subscribe

[1] Joao Monteiro,Jahangir Alam,Tiago H. Falk, "End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4916. Accessed: Nov. 11, 2019.
@article{4916-19,
url = {http://sigport.org/4916},
author = {Joao Monteiro;Jahangir Alam;Tiago H. Falk },
publisher = {IEEE SigPort},
title = {End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks},
year = {2019} }
TY - EJOUR
T1 - End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks
AU - Joao Monteiro;Jahangir Alam;Tiago H. Falk
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4916
ER -
Joao Monteiro,Jahangir Alam,Tiago H. Falk. (2019). End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks. IEEE SigPort. http://sigport.org/4916
Joao Monteiro,Jahangir Alam,Tiago H. Falk, 2019. End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks. Available at: http://sigport.org/4916.
Joao Monteiro,Jahangir Alam,Tiago H. Falk. (2019). "End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks." Web.
1. Joao Monteiro,Jahangir Alam,Tiago H. Falk. End-to-end Detection of Attacks to Automatic Speaker Recognizers with Time-attentive Light Convolutional Neural Networks [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4916