Paper Info
Title
Audio Replay Attack Detection Using High-Frequency Features
Abstract
This paper presents our contribution to the ASVspoof 2017 Challenge. It addresses a replay spoofing attack against a speaker recognition system by detecting that the analysed signal has passed through multiple analogue-to-digital (AD) conversions. Specifically, we show that most of the cues that enable to detect the replay attacks can be found in the high-frequency band of the replayed recordings. The described anti-spoofing countermeasures are based on (1) modelling the subband spectrum and (2) using the proposed features derived from the linear prediction (LP) analysis. The results of the investigated methods show a significant improvement in comparison to the baseline system of the ASVspoof 2017 Challenge. A relative equal error rate (EER) reduction by 70% was achieved for the development set and a reduction by 30% was obtained for the evaluation set.
Year
DOI
Venue
2017
10.21437/Interspeech.2017-776
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION
Keywords
Field
DocType
anti-spoofing, replay detection, playback detection, speaker recognition
Computer science,Speech recognition,Replay attack
Conference
ISSN
Citations 
PageRank 
2308-457X
11
0.62
References 
Authors
6
5
Name
Order
Citations
PageRank
Marcin Witkowski1152.44
Stanisław Kacprzak2162.73
Piotr Zelasko3209.39
Konrad Kowalczyk48113.57
Jakub Galka5447.47