Self-supervised Text-independent Speaker Verification Using Prototypical Momentum Contrastive Learning

Abstract

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo speaker embedding system utilizes a queue to maintain a large set of negative examples. We show that better speaker embeddings can be learned by momentum contrastive learning. Next, alternative augmentation strategies are explored to normalize extrinsic speaker variabilities of two random segments from the same speech utterance. Specifically, augmentation in the waveform largely improves the speaker representations for SV tasks. The proposed MoCo speaker embedding is further improved when a prototypical memory bank is introduced, which encourages the speaker embeddings to be closer to their assigned prototypes with an intermediate clustering step. In addition, we generalize the self-supervised framework to a semi-supervised scenario where only a small p

Stats

• citations52
• S2 citations—
• github stars0
• HF likes0
• heat score12.93
• arxiv keyxia2020self

Related papers

• Momentum Contrast Speaker Representation Learning (2020)0.00
• Label-efficient Self-supervised Speaker Verification With Information Maximization And Contrastive Learning (2022)6.77
• Additive Margin In Contrastive Self-supervised Frameworks To Learn Discriminative Speaker Representations (2024)2.26
• Asymmetric Clean Segments-guided Self-supervised Learning For Robust Speaker Verification (2023)5.84
• Experimenting With Additive Margins For Contrastive Self-supervised Speaker Verification (2023)4.52
• Self-supervised Speaker Verification With Simple Siamese Network And Self-supervised Regularization (2021)10.85
• Discriminative Speaker Representation Via Contrastive Learning With Class-aware Attention In Angular Space (2022)8.60
• Self-distillation Prototypes Network: Learning Robust Speaker Representations Without Supervision (2023)4.52