ATMM-SAGA: Alternating Training for Multi-Module with Score-Aware Gated Attention SASV system

The objective of automatic speaker verification (ASV) systems is to determine whether a given test speech utterance corresponds to a claimed enrolled speaker. These systems have a wide range of applications, and ensuring their reliability is crucial. In this paper, we propose a spoofing-robust automatic speaker verification (SASV) system employing a score-aware gated attention (SAGA) fusion scheme, integrating scores from a pre-trained countermeasure (CM) with speaker embeddings from a pre-trained ASV. Specifically, we employ the AASIST and ECAPA-TDNN models. SAGA acts as an adaptive gating mechanism, where the CM score determines how strongly ASV embeddings influence the final SASV decision. Experiments on the ASVspoof2019 logical access dataset demonstrate that the proposed SASV system achieves an SASV equal error rate (SASV-EER) and agnostic detection cost function (a-DCF) of 2.31%, 0.0603 for the development set and 2.18%, 0.0480 for the evaluation set.

ASVspoof2019 vs. ASVspoof5: Assessment and Comparison

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.

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

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.

a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verification

Spoofing detection is today a mainstream research topic. Standard metrics can be applied to evaluate the performance of isolated spoofing detection solutions and others have been proposed to support their evaluation when they are combined with speaker detection. These either have well-known deficiencies or restrict the architectural approach to combine speaker and spoof detectors. In this paper, we propose an architecture-agnostic detection cost function (a-DCF). A generalisation of the original DCF used widely for the assessment of automatic speaker verification (ASV), the a-DCF is designed for the evaluation of spoofing-robust ASV. Like the DCF, the a-DCF reflects the cost of decisions in a Bayes risk sense, with explicitly defined class priors and detection cost model. We demonstrate the merit of the a-DCF through the benchmarking evaluation of architecturally-heterogeneous spoofing-robust ASV solutions.

Stochastic mean-shift clustering

In this paper we presented a stochastic version mean-shift clustering algorithm. In the stochastic version the data points "climb" to the modes of the distribution collectively, while in the deterministic mean-shift, each datum "climbs" individually, while all other data points remains in their original coordinates. Stochastic version of the mean-shift clustering is comparison with a standard (deterministic) mean-shift clustering on synthesized 2- and 3-dimensional data distributed between several Gaussian component. The comparison performed in terms of cluster purity and class data purity. It was found the the stochastic mean-shift clustering outperformed in most of the cases the deterministic mean-shift.

Thech. Report: Genuinization of Speech waveform PMF for speaker detection spoofing and countermeasures

In the context of spoofing attacks in speaker recognition systems, we observed that the waveform probability mass function (PMF) of genuine speech differs significantly from the PMF of speech resulting from the attacks. This is true for synthesized or converted speech as well as replayed speech. We also noticed that this observation seems to have a significant impact on spoofing detection performance. In this article, we propose an algorithm, denoted genuinization, capable of reducing the waveform distribution gap between authentic speech and spoofing speech. Our genuinization algorithm is evaluated on ASVspoof 2019 challenge datasets, using the baseline system provided by the challenge organization. We first assess the influence of genuinization on spoofing performance. Using genuinization for the spoofing attacks degrades spoofing detection performance by up to a factor of 10. Next, we integrate the genuinization algorithm in the spoofing countermeasures and we observe a huge spoofing detection improvement in different cases. The results of our experiments show clearly that waveform distribution plays an important role and must be taken into account by anti-spoofing systems.

Time-Domain Based Embeddings for Spoofed Audio Representation

Anti-spoofing is the task of speech authentication. That is, identifying genuine human speech compared to spoofed speech. The main focus of this paper is to suggest new representations for genuine and spoofed speech, based on the probability mass function (PMF) estimation of the audio waveforms' amplitude. We introduce a new feature extraction method for speech audio signals: unlike traditional methods, our method is based on direct processing of time-domain audio samples. The PMF is utilized by designing a feature extractor based on different PMF distances and similarity measures. As an additional step, we used filter-bank preprocessing, which significantly affects the discriminative characteristics of the features and facilitates convenient visualization of possible clustering of spoofing attacks. Furthermore, we use diffusion maps to reveal the underlying manifold on which the data lies. The suggested embeddings allow the use of simple linear separators to achieve decent performance. In addition, we present a convenient way to visualize the data, which helps to assess the efficiency of different spoofing techniques. The experimental results show the potential of using multi-channel PMF based features for the anti-spoofing task, in addition to the benefits of using diffusion maps both as an analysis tool and as an embedding tool.