Texture-based Presentation Attack Detection for Automatic Speaker Verification

TL;DR

This paper introduces a texture descriptor-based approach using Fisher vector features for presentation attack detection in automatic speaker verification, demonstrating improved generalisability and accuracy in distinguishing genuine from attack speech.

Contribution

It proposes a novel texture analysis method with Fisher vector features for PAD, enhancing detection robustness beyond ensemble classifier approaches.

Findings

High detection accuracy with only 16% false rejections of genuine presentations

Low false acceptance rate of 1% for attack presentations

Effective generalisability across different attack types

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.