Tandem spoofing-robust automatic speaker verification based on time-domain embeddings

TL;DR

This paper introduces a novel time-domain embedding method based on the probability mass function of waveform amplitudes for spoofing-robust speaker verification, emphasizing gender-specific features and fusion with traditional systems to improve detection accuracy.

Contribution

The study presents a new time-domain embedding approach using PMF of waveform amplitudes, incorporating gender recognition and fusion techniques to enhance spoofing detection in speaker verification.

Findings

Gender recognition accuracy with mismatch rates of 0.94% (male) and 1.79% (female)

Equal error rates of 8.67% (male) and 10.12% (female) in gender-specific CM systems

Fusion with traditional systems improves generalization and detection performance.

Abstract

Spoofing-robust automatic speaker verification (SASV) systems are a crucial technology for the protection against spoofed speech. In this study, we focus on logical access attacks and introduce a novel approach to SASV tasks. A novel representation of genuine and spoofed speech is employed, based on the probability mass function (PMF) of waveform amplitudes in the time domain. This methodology generates novel time embeddings derived from the PMF of selected groups within the training set. This paper highlights the role of gender segregation and its positive impact on performance. We propose a countermeasure (CM) system that employs time-domain embeddings derived from the PMF of spoofed and genuine speech, as well as gender recognition based on male and female time-based embeddings. The method exhibits notable gender recognition capabilities, with mismatch rates of 0.94% and 1.79% for males and females, respectively. The male and female CM systems achieve an equal error rate (EER) of 8.67% and 10.12%, respectively. By integrating this approach with traditional speaker verification systems, we demonstrate improved generalization ability and tandem detection cost function evaluation using the ASVspoof2019 challenge database. Furthermore, we investigate the impact of fusing the time embedding approach with traditional CM and illustrate how this fusion enhances generalization in SASV architectures.