论文标题
2022年欺骗扬声器验证挑战的DKU-OPPO系统
The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge
论文作者
论文摘要
本文介绍了我们的DKU-OPPO系统，用于2022年的Spoofing-Awane Speaker验证（SASV）挑战。首先，我们将联合任务分为说话者验证（SV）和欺骗对策（CM），这两个任务是分别优化的。对于ASV系统，采用了四种最先进的方法。对于CM系统，我们在挑战基线的基础上提出了两种方法，以进一步提高性能，即嵌入随机抽样增强（ERSA）（ERSA）和一级混乱损失（OCCL）。其次，我们还探讨了SV嵌入是否可以帮助改善CM系统性能。我们观察到现有CM系统在域不匹配的Voxceleb2数据集上的急剧性能下降。第三，我们比较不同的融合策略，包括平行得分融合和顺序级联系统。与1.71％的SASV-EER基线相比，我们提交的级联系统在挑战官员评估集中获得了0.21％的SASV-EER。
This paper describes our DKU-OPPO system for the 2022 Spoofing-Aware Speaker Verification (SASV) Challenge. First, we split the joint task into speaker verification (SV) and spoofing countermeasure (CM), these two tasks which are optimized separately. For ASV systems, four state-of-the-art methods are employed. For CM systems, we propose two methods on top of the challenge baseline to further improve the performance, namely Embedding Random Sampling Augmentation (ERSA) and One-Class Confusion Loss(OCCL). Second, we also explore whether SV embedding could help improve CM system performance. We observe a dramatic performance degradation of existing CM systems on the domain-mismatched Voxceleb2 dataset. Third, we compare different fusion strategies, including parallel score fusion and sequential cascaded systems. Compared to the 1.71% SASV-EER baseline, our submitted cascaded system obtains a 0.21% SASV-EER on the challenge official evaluation set.
