Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification
This work addresses speaker verification for unlabeled speech data, presenting incremental improvements over existing self-supervised techniques.
The paper tackled improving self-supervised speaker verification by introducing a symmetric contrastive loss and additive margins, achieving 7.50% EER and 0.5804 minDCF on VoxCeleb1, outperforming other contrastive methods.
Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We explore different ways to improve the performance of these methods by: (1) revisiting how positive and negative pairs are sampled through a "symmetric" formulation of the contrastive loss; (2) introducing margins similar to AM-Softmax and AAM-Softmax that have been widely adopted in the supervised setting. We demonstrate the effectiveness of the symmetric contrastive loss which provides more supervision for the self-supervised task. Moreover, we show that Additive Margin and Additive Angular Margin allow reducing the overall number of false negatives and false positives by improving speaker separability. Finally, by combining both techniques and training a larger model we achieve 7.50% EER and 0.5804 minDCF on the VoxCeleb1 test set, which outperforms other contrastive self supervised methods on speaker verification.