Is Audio Spoof Detection Robust to Laundering Attacks?

TL;DR

This paper assesses the robustness of state-of-the-art audio spoof detection methods against laundering attacks, revealing significant performance degradation and highlighting the need for more resilient detection techniques.

Contribution

It introduces a new laundering attack database and evaluates existing SOTA spoof detection approaches, exposing their vulnerabilities to laundering attacks.

Findings

SOTA systems perform poorly against laundering attacks

Reverberation and noise attacks significantly degrade detection accuracy

Highlights the need for developing robust spoof detection methods

Abstract

Voice-cloning (VC) systems have seen an exceptional increase in the realism of synthesized speech in recent years. The high quality of synthesized speech and the availability of low-cost VC services have given rise to many potential abuses of this technology. Several detection methodologies have been proposed over the years that can detect voice spoofs with reasonably good accuracy. However, these methodologies are mostly evaluated on clean audio databases, such as ASVSpoof 2019. This paper evaluates SOTA Audio Spoof Detection approaches in the presence of laundering attacks. In that regard, a new laundering attack database, called the ASVSpoof Laundering Database, is created. This database is based on the ASVSpoof 2019 (LA) eval database comprising a total of 1388.22 hours of audio recordings. Seven SOTA audio spoof detection approaches are evaluated on this laundered database. The results indicate that SOTA systems perform poorly in the presence of aggressive laundering attacks, especially reverberation and additive noise attacks. This suggests the need for robust audio spoof detection.