Spoofing-Aware Speaker Verification by Multi-Level Fusion

TL;DR

This paper introduces a multi-level fusion approach combining multiple models and features to improve spoofing-aware speaker verification, achieving state-of-the-art results on the SASV challenge.

Contribution

It proposes a novel multi-model, multi-level fusion framework that integrates CM and ASV scores for enhanced spoofing-aware speaker verification.

Findings

Achieved SASV-EER of 0.97% with the best single fusion system.

Ensembling top-5 fusion systems reduced SASV-EER to 0.89%.

Demonstrated the effectiveness of multi-level fusion in SASV tasks.

Abstract

Recently, many novel techniques have been introduced to deal with spoofing attacks, and achieve promising countermeasure (CM) performances. However, these works only take the stand-alone CM models into account. Nowadays, a spoofing aware speaker verification (SASV) challenge which aims to facilitate the research of integrated CM and ASV models, arguing that jointly optimizing CM and ASV models will lead to better performance, is taking place. In this paper, we propose a novel multi-model and multi-level fusion strategy to tackle the SASV task. Compared with purely scoring fusion and embedding fusion methods, this framework first utilizes embeddings from CM models, propagating CM embeddings into a CM block to obtain a CM score. In the second-level fusion, the CM score and ASV scores directly from ASV systems will be concatenated into a prediction block for the final decision. As a result, the best single fusion system has achieved the SASV-EER of 0.97% on the evaluation set. Then by ensembling the top-5 fusion systems, the final SASV-EER reached 0.89%.