13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Spoofing Countermeasures for the Protection of Automatic Speaker Recognition Systems Against Attacks With Artificial Signals

Federico Alegre, Ravichander Vipperla, Nicholas Evans

Multimedia Communications Department, EURECOM, Sophia Antipolis, France

The vulnerability of automatic speaker recognition systems to imposture or spoofing is widely acknowledged. This paper shows that extremely high false alarm rates can be provoked by simple spoofing attacks with artificial, non-speech-like signals and highlights the need for spoofing countermeasures. We show that two new, but trivial countermeasures based on higher-level, dynamic features and voice quality assessment offer varying degrees of protection and that further work is needed to develop more robust spoofing countermeasure mechanisms. Finally, we show that certain classifiers are inherently more robust to such attacks than others which strengthens the case for fused-system approaches to automatic speaker recognition.

Index Terms: automatic speaker verification, biometrics, spoofing, imposture, countermeasures

Full Paper

Bibliographic reference.  Alegre, Federico / Vipperla, Ravichander / Evans, Nicholas (2012): "Spoofing countermeasures for the protection of automatic speaker recognition systems against attacks with artificial signals", In INTERSPEECH-2012, 1688-1691.