Semi-supervised Contrastive Learning With Generalized Contrastive Loss And Its Application To Speaker Recognition

Abstract

This paper introduces a semi-supervised contrastive learning framework and its application to text-independent speaker verification. The proposed framework employs generalized contrastive loss (GCL). GCL unifies losses from two different learning frameworks, supervised metric learning and unsupervised contrastive learning, and thus it naturally determines the loss for semi-supervised learning. In experiments, we applied the proposed framework to text-independent speaker verification on the VoxCeleb dataset. We demonstrate that GCL enables the learning of speaker embeddings in three manners, supervised learning, semi-supervised learning, and unsupervised learning, without any changes in the definition of the loss function.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyinoue2020semi

Related papers

• Discriminative Speaker Representation Via Contrastive Learning With Class-aware Attention In Angular Space (2022)8.60
• Momentum Contrast Speaker Representation Learning (2020)0.00
• Unsupervised Representation Learning For Speaker Recognition Via Contrastive Equilibrium Learning (2020)0.00
• Asymmetric Clean Segments-guided Self-supervised Learning For Robust Speaker Verification (2023)5.84
• A Comparison Of Metric Learning Loss Functions For End-to-end Speaker Verification (2020)6.77
• Self-supervised Speaker Verification Using Dynamic Loss-gate And Label Correction (2022)10.74
• Additive Margin In Contrastive Self-supervised Frameworks To Learn Discriminative Speaker Representations (2024)2.26
• Self-supervised Speaker Recognition With Loss-gated Learning (2021)16.93