ASVspoof2019 vs. ASVspoof5: Assessment and Comparison

TL;DR

This paper compares the ASVspoof2019 and ASVspoof5 challenges, highlighting how the latter introduces more complex mismatched conditions, making spoofing detection more challenging and revealing shifts in speech characteristics.

Contribution

It provides a detailed assessment of database condition differences between ASVspoof2019 and ASVspoof5, emphasizing the increased difficulty and speech shifts in the newer challenge.

Findings

ASVspoof5 presents more challenging spoofing attacks.

Genuine speech in ASVspoof5 shifts toward spoofed speech.

Mismatched conditions are more extensive in ASVspoof5.

Abstract

ASVspoof challenges are designed to advance the understanding of spoofing speech attacks and encourage the development of robust countermeasure systems. These challenges provide a standardized database for assessing and comparing spoofing-robust automatic speaker verification solutions. The ASVspoof5 challenge introduces a shift in database conditions compared to ASVspoof2019. While ASVspoof2019 has mismatched conditions only in spoofing attacks in the evaluation set, ASVspoof5 incorporates mismatches in both bona fide and spoofed speech statistics. This paper examines the impact of these mismatches, presenting qualitative and quantitative comparisons within and between the two databases. We show the increased difficulty for genuine and spoofed speech and demonstrate that in ASVspoof5, not only are the attacks more challenging, but the genuine speech also shifts toward spoofed speech compared to ASVspoof2019.