Integrated Replay Spoofing-Aware Text-Independent Speaker Verification

Abstract

A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for building an integrated system of speaker verification and presentation attack detection: an end-to-end monolithic approach and a back-end modular approach. The first approach simultaneously trains speaker identification, presentation attack detection, and the integrated system using multi-task learning using a common feature. However, through experiments, we hypothesize that the information required for performing speaker verification and presentation attack detection might differ because speaker verification systems try to remove device-specific information from speaker embeddings, while presentation attack detection systems exploit such information. Therefore, we propose a back-end modular approach using a separate deep neural network (DNN) for speaker verification and presentation attack detection. This approach has thee input components: two speaker embeddings (for enrollment and test each) and prediction of presentation attacks. Experiments are conducted using the ASVspoof 2017-v2 dataset, which includes official trials on the integration of speaker verification and presentation attack detection. The proposed back-end approach demonstrates a relative improvement of 21.77% in terms of the equal error rate for integrated trials compared to a conventional speaker verification system.

AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks

“…Third, we present a new readout scheme that utilizes the stack node. Finally, given the application of anti-spoofing solutions in aasisting speaker verification systems [18,19] and given the associated requirement for practical, lightweight models, we further propose a lightweight variant of AA-SIST which comprises only 85K parameters.…”

A Probabilistic Fusion Framework for Spoofing Aware Speaker Verification

“…Kanervisto et al [22] proposed a reinforcement learning paradigm to optimize tandem detection cost function (t-DCF) by jointly training a tandem ASV and CM system. Shim et al [23] proposed a fusion-based approach that takes the speaker embedding and CM prediction as input and weighs the ASV score, CM score, and their multiplication to make the final decision.…”

SASV Challenge 2022: A Spoofing Aware Speaker Verification Challenge Evaluation Plan

“…The goal of the new SASV challenge is hence to further improve robustness to both zero-effort impostor access attempts and spoofing attacks by providing a framework to support the optimisation of CM and ASV systems operating in tandem and, ultimately, facilitate the development of single integrated systems. With only relatively little previous work in this direction [24][25][26][27][28], the objectives of the first challenge are to:…”