Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation
This addresses the need for more reliable spoofing countermeasures in speaker verification systems, though it is incremental as it builds on existing self-supervised learning methods.
The paper tackled the problem of spoofing and deepfake detection in automatic speaker verification by using a wav2vec 2.0 front-end with fine-tuning and data augmentation, achieving the lowest equal error rates on ASVspoof 2021 databases and an 90% improvement over the baseline.
The performance of spoofing countermeasure systems depends fundamentally upon the use of sufficiently representative training data. With this usually being limited, current solutions typically lack generalisation to attacks encountered in the wild. Strategies to improve reliability in the face of uncontrolled, unpredictable attacks are hence needed. We report in this paper our efforts to use self-supervised learning in the form of a wav2vec 2.0 front-end with fine tuning. Despite initial base representations being learned using only bona fide data and no spoofed data, we obtain the lowest equal error rates reported in the literature for both the ASVspoof 2021 Logical Access and Deepfake databases. When combined with data augmentation,these results correspond to an improvement of almost 90% relative to our baseline system.