Texture-based Presentation Attack Detection for Automatic Speaker Verification - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Texture-based Presentation Attack Detection for Automatic Speaker Verification

Abstract

Biometric systems are nowadays employed across a broad range of applications. They provide high security and efficiency and, in many cases, are user friendly. Despite these and other advantages, biometric systems in general and Automatic speaker verification (ASV) systems in particular can be vulnerable to attack presentations. The most recent ASVSpoof 2019 competition showed that most forms of attacks can be detected reliably with ensemble classifier-based presentation attack detection (PAD) approaches. These, though, depend fundamentally upon the complementarity of systems in the ensemble. With the motivation to increase the generalisability of PAD solutions, this paper reports our exploration of texture descriptors applied to the analysis of speech spectrogram images. In particular, we propose a common fisher vector feature space based on a generative model. Experimental results show the soundness of our approach: at most, 16 in 100 bona fide presentations are rejected whereas only one in 100 attack presentations are accepted.

Dates and versions

hal-03560804 , version 1 (07-02-2022)

Identifiers

Cite

Lazaro Gonzalez-Soler, Jose Patino, Marta Gomez-Barrero, Massimiliano Todisco, Christoph Busch, et al.. Texture-based Presentation Attack Detection for Automatic Speaker Verification. 2020 IEEE International Workshop on Information Forensics and Security (WIFS), Dec 2020, New York, United States. pp.1-6, ⟨10.1109/WIFS49906.2020.9360882⟩. ⟨hal-03560804⟩

Collections

EURECOM ANR
26 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More