Backend Ensemble for Speaker Verification and Spoofing Countermeasure

TL;DR

This paper presents a novel backend ensemble approach for speaker verification and spoofing detection, utilizing circulant matrix transformations, convolutional fusion, and attention mechanisms to improve performance in SASV tasks.

Contribution

It introduces new embedding transformation and fusion techniques, including circulant matrix stacking and attention-based neural networks, for enhanced speaker verification and anti-spoofing.

Findings

Achieved state-of-the-art SASV-EER of 0.559%

Demonstrated effectiveness of circulant embedding and attention mechanisms

System ranked fifth in the challenge

Abstract

This paper describes the NPU system submitted to Spoofing Aware Speaker Verification Challenge 2022. We particularly focus on the \textit{backend ensemble} for speaker verification and spoofing countermeasure from three aspects. Firstly, besides simple concatenation, we propose circulant matrix transformation and stacking for speaker embeddings and countermeasure embeddings. With the stacking operation of newly-defined circulant embeddings, we almost explore all the possible interactions between speaker embeddings and countermeasure embeddings. Secondly, we attempt different convolution neural networks to selectively fuse the embeddings' salient regions into channels with convolution kernels. Finally, we design parallel attention in 1D convolution neural networks to learn the global correlation in channel dimensions as well as to learn the important parts in feature dimensions. Meanwhile, we embed squeeze-and-excitation attention in 2D convolutional neural networks to learn the global dependence among speaker embeddings and countermeasure embeddings. Experimental results demonstrate that all the above methods are effective. After fusion of four well-trained models enhanced by the mentioned methods, the best SASV-EER, SPF-EER and SV-EER we achieve are 0.559\%, 0.354\% and 0.857\% on the evaluation set respectively. Together with the above contributions, our submission system achieves the fifth place in this challenge.