Self-supervised Speaker Recognition With Loss-gated Learning

Abstract

In self-supervised learning for speaker recognition, pseudo labels are useful as the supervision signals. It is a known fact that a speaker recognition model doesn't always benefit from pseudo labels due to their unreliability. In this work, we observe that a speaker recognition network tends to model the data with reliable labels faster than those with unreliable labels. This motivates us to study a loss-gated learning (LGL) strategy, which extracts the reliable labels through the fitting ability of the neural network during training. With the proposed LGL, our speaker recognition model obtains a \(46.3%\) performance gain over the system without it. Further, the proposed self-supervised speaker recognition with LGL trained on the VoxCeleb2 dataset without any labels achieves an equal error rate of \(1.66%\) on the VoxCeleb1 original test set. Code has been made available at: https://github.com/TaoRuijie/Loss-Gated-Learning.

Stats

• citations53
• S2 citations—
• github stars92
• HF likes0
• heat score16.93
• arxiv keytao2021self

Code

• TaoRuijie/Loss-Gated-Learning—

Related papers

• Self-supervised Speaker Verification Using Dynamic Loss-gate And Label Correction (2022)10.74
• Augmentation Adversarial Training For Self-supervised Speaker Recognition (2020)0.00
• Improving Pseudo-label Training For End-to-end Speech Recognition Using Gradient Mask (2021)5.84
• Self-supervised Reflective Learning Through Self-distillation And Online Clustering For Speaker Representation Learning (2024)2.26
• Self-supervised Speaker Verification With Simple Siamese Network And Self-supervised Regularization (2021)10.85
• Why Does Self-supervised Learning For Speech Recognition Benefit Speaker Recognition? (2022)10.74
• Semi-supervised Contrastive Learning With Generalized Contrastive Loss And Its Application To Speaker Recognition (2020)0.00
• Self-supervised Learning Based Domain Adaptation For Robust Speaker Verification (2021)11.49