Self-supervised Speaker Verification With Simple Siamese Network And Self-supervised Regularization

Abstract

Training speaker-discriminative and robust speaker verification systems without speaker labels is still challenging and worthwhile to explore. In this study, we propose an effective self-supervised learning framework and a novel regularization strategy to facilitate self-supervised speaker representation learning. Different from contrastive learning-based self-supervised learning methods, the proposed self-supervised regularization (SSReg) focuses exclusively on the similarity between the latent representations of positive data pairs. We also explore the effectiveness of alternative online data augmentation strategies on both the time domain and frequency domain. With our strong online data augmentation strategy, the proposed SSReg shows the potential of self-supervised learning without using negative pairs and it can significantly improve the performance of self-supervised speaker representation learning with a simple Siamese network architecture. Comprehensive experiments on the VoxC

Stats

• citations27
• S2 citations—
• github stars0
• HF likes0
• heat score10.85
• arxiv keysang2021self

Related papers

• Self-distillation Prototypes Network: Learning Robust Speaker Representations Without Supervision (2023)4.52
• Pushing The Limits Of Self-supervised Speaker Verification Using Regularized Distillation Framework (2022)17.00
• Asymmetric Clean Segments-guided Self-supervised Learning For Robust Speaker Verification (2023)5.84
• Augmentation Adversarial Training For Self-supervised Speaker Recognition (2020)0.00
• Curriculum Learning For Self-supervised Speaker Verification (2022)8.09
• Self-supervised Learning Based Domain Adaptation For Robust Speaker Verification (2021)11.49
• An Iterative Framework For Self-supervised Deep Speaker Representation Learning (2020)10.61
• Label-efficient Self-supervised Speaker Verification With Information Maximization And Contrastive Learning (2022)6.77