C3-DINO: Joint Contrastive And Non-contrastive Self-supervised Learning For Speaker Verification

Abstract

Self-supervised learning (SSL) has drawn an increased attention in the field of speech processing. Recent studies have demonstrated that contrastive learning is able to learn discriminative speaker embeddings in a self-supervised manner. However, base contrastive self-supervised learning (CSSL) assumes that the pairs generated from a view of anchor instance and any view of other instances are all negative, which introduces many false negative pairs in constructing the loss function. The problem is referred as \(class\)-\(collision\), which remains as one major issue that impedes the CSSL based speaker verification (SV) systems from achieving better performances. In the meanwhile, studies reveal that negative sample free SSL frameworks perform well in learning speaker or image representations. In this study, we investigate SSL techniques that lead to an improved SV performance. We first analyse the impact of false negative pairs in the CSSL systems. Then, a multi-stage Class-Collision C

Stats

• citations22
• S2 citations—
• github stars0
• HF likes0
• heat score10.21
• arxiv keyzhang2022c3

Related papers

• 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
• Towards Supervised Performance On Speaker Verification With Self-supervised Learning By Leveraging Large-scale ASR Models (2024)7.50
• Non-contrastive Self-supervised Learning For Utterance-level Information Extraction From Speech (2022)9.59
• What Do Self-supervised Speech And Speaker Models Learn? New Findings From A Cross Model Layer-wise Analysis (2024)8.09
• Experimenting With Additive Margins For Contrastive Self-supervised Speaker Verification (2023)4.52
• Self-supervised Learning Of Audio Representations Using Angular Contrastive Loss (2022)5.84
• Multi-variant Consistency Based Self-supervised Learning For Robust Automatic Speech Recognition (2021)0.00