Additive Margin In Contrastive Self-supervised Frameworks To Learn Discriminative Speaker Representations

Abstract

Self-Supervised Learning (SSL) frameworks became the standard for learning robust class representations by benefiting from large unlabeled datasets. For Speaker Verification (SV), most SSL systems rely on contrastive-based loss functions. We explore different ways to improve the performance of these techniques by revisiting the NT-Xent contrastive loss. Our main contribution is the definition of the NT-Xent-AM loss and the study of the importance of Additive Margin (AM) in SimCLR and MoCo SSL methods to further separate positive from negative pairs. Despite class collisions, we show that AM enhances the compactness of same-speaker embeddings and reduces the number of false negatives and false positives on SV. Additionally, we demonstrate the effectiveness of the symmetric contrastive loss, which provides more supervision for the SSL task. Implementing these two modifications to SimCLR improves performance and results in 7.85% EER on VoxCeleb1-O, outperforming other equivalent methods.

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keylepage2024additive

Related papers

• Experimenting With Additive Margins For Contrastive Self-supervised Speaker Verification (2023)4.52
• C3-DINO: Joint Contrastive And Non-contrastive Self-supervised Learning For Speaker Verification (2022)10.21
• Towards Supervised Performance On Speaker Verification With Self-supervised Learning By Leveraging Large-scale ASR Models (2024)7.50
• Self-supervised Text-independent Speaker Verification Using Prototypical Momentum Contrastive Learning (2020)12.93
• Asymmetric Clean Segments-guided Self-supervised Learning For Robust Speaker Verification (2023)5.84
• Discriminative Speaker Representation Via Contrastive Learning With Class-aware Attention In Angular Space (2022)8.60
• Self-supervised Learning Of Audio Representations Using Angular Contrastive Loss (2022)5.84
• Label-efficient Self-supervised Speaker Verification With Information Maximization And Contrastive Learning (2022)6.77