Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion

TL;DR

This paper evaluates the integration of speaker verification and spoofing countermeasures, demonstrating that fusion strategies significantly improve system robustness against spoofing attacks, and introduces a new challenge for benchmarking such integrated solutions.

Contribution

It presents a comprehensive analysis of score and embedding fusion methods for spoofing-aware speaker verification and introduces the SASV challenge for standardized benchmarking.

Findings

Fusion strategies reduce EER from 23.83% to below 7%.

Integrated systems outperform standalone solutions significantly.

The SASV challenge promotes development of more robust speaker verification methods.

Abstract

Deep learning has brought impressive progress in the study of both automatic speaker verification (ASV) and spoofing countermeasures (CM). Although solutions are mutually dependent, they have typically evolved as standalone sub-systems whereby CM solutions are usually designed for a fixed ASV system. The work reported in this paper aims to gauge the improvements in reliability that can be gained from their closer integration. Results derived using the popular ASVspoof2019 dataset indicate that the equal error rate (EER) of a state-of-the-art ASV system degrades from 1.63% to 23.83% when the evaluation protocol is extended with spoofed trials.%subjected to spoofing attacks. However, even the straightforward integration of ASV and CM systems in the form of score-sum and deep neural network-based fusion strategies reduce the EER to 1.71% and 6.37%, respectively. The new Spoofing-Aware Speaker Verification (SASV) challenge has been formed to encourage greater attention to the integration of ASV and CM systems as well as to provide a means to benchmark different solutions.