Self-Supervised Speaker Verification Using Dynamic Loss-Gate and Label Correction

08/03/2022
by   Bing Han, et al.
0

For self-supervised speaker verification, the quality of pseudo labels decides the upper bound of the system due to the massive unreliable labels. In this work, we propose dynamic loss-gate and label correction (DLG-LC) to alleviate the performance degradation caused by unreliable estimated labels. In DLG, we adopt Gaussian Mixture Model (GMM) to dynamically model the loss distribution and use the estimated GMM to distinguish the reliable and unreliable labels automatically. Besides, to better utilize the unreliable data instead of dropping them directly, we correct the unreliable label with model predictions. Moreover, we apply the negative-pairs-free DINO framework in our experiments for further improvement. Compared to the best-known speaker verification system with self-supervised learning, our proposed DLG-LC converges faster and achieves 11.45 Vox-O, Vox-E and Vox-H trials of Voxceleb1 evaluation dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/12/2023

Self-Supervised Learning with Cluster-Aware-DINO for High-Performance Robust Speaker Verification

Automatic speaker verification task has made great achievements using de...
research
11/22/2022

OR-Gate: A Noisy Label Filtering Method for Speaker Verification

The deep learning models used for speaker verification are heavily depen...
research
10/25/2020

An iterative framework for self-supervised deep speaker representation learning

In this paper, we propose an iterative framework for self-supervised spe...
research
11/08/2022

Pushing the limits of self-supervised speaker verification using regularized distillation framework

Training robust speaker verification systems without speaker labels has ...
research
06/16/2023

Evaluation of Speech Representations for MOS prediction

In this paper, we evaluate feature extraction models for predicting spee...
research
09/19/2022

SJTU-AISPEECH System for VoxCeleb Speaker Recognition Challenge 2022

This report describes the SJTU-AISPEECH system for the Voxceleb Speaker ...
research
09/07/2021

The DKU-DukeECE System for the Self-Supervision Speaker Verification Task of the 2021 VoxCeleb Speaker Recognition Challenge

This report describes the submission of the DKU-DukeECE team to the self...

Please sign up or login with your details

Forgot password? Click here to reset