A comprehensive study on self-supervised distillation for speaker representation learning

10/28/2022
by   Zhengyang Chen, et al.
0

In real application scenarios, it is often challenging to obtain a large amount of labeled data for speaker representation learning due to speaker privacy concerns. Self-supervised learning with no labels has become a more and more promising way to solve it. Compared with contrastive learning, self-distilled approaches use only positive samples in the loss function and thus are more attractive. In this paper, we present a comprehensive study on self-distilled self-supervised speaker representation learning, especially on critical data augmentation. Our proposed strategy of audio perturbation augmentation has pushed the performance of the speaker representation to a new limit. The experimental results show that our model can achieve a new SoTA on Voxceleb1 speaker verification evaluation benchmark ( i.e., equal error rate (EER) 2.505 respectively), discarding any speaker labels in the training phase.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/08/2021

Self-Supervised Speaker Verification with Simple Siamese Network and Self-Supervised Regularization

Training speaker-discriminative and robust speaker verification systems ...
research
12/13/2020

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

In this study, we investigate self-supervised representation learning fo...
research
08/09/2023

Speaker Recognition Using Isomorphic Graph Attention Network Based Pooling on Self-Supervised Representation

The emergence of self-supervised representation (i.e., wav2vec 2.0) allo...
research
08/05/2023

Self-Distillation Network with Ensemble Prototypes: Learning Robust Speaker Representations without Supervision

Training speaker-discriminative and robust speaker verification systems ...
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
07/12/2022

Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning

State-of-the-art speaker verification systems are inherently dependent o...
research
10/12/2021

UniSpeech-SAT: Universal Speech Representation Learning with Speaker Aware Pre-Training

Self-supervised learning (SSL) is a long-standing goal for speech proces...

Please sign up or login with your details

Forgot password? Click here to reset