DeepAI
Log In Sign Up

Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning

10/22/2020
by   Sung Hwan Mun, et al.
0

In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty on nuisance factors latent in the embeddings by employing the uniformity loss. Also, to preserve speaker discriminability, a contrastive similarity loss function is used together. Experimental results showed that the proposed CEL significantly outperforms the state-of-the-art unsupervised speaker verification systems and the best performing model achieved 8.01 respectively. On top of that, the performance of the supervised speaker embedding networks trained with initial parameters pre-trained via CEL showed better performance than those trained with randomly initialized parameters.

READ FULL TEXT

page 1

page 2

page 3

page 4

06/08/2020

Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition

This paper introduces a semi-supervised contrastive learning framework a...
10/22/2020

Momentum Contrast Speaker Representation Learning

Unsupervised representation learning has shown remarkable achievement by...
08/10/2022

Non-Contrastive Self-Supervised Learning of Utterance-Level Speech Representations

Considering the abundance of unlabeled speech data and the high labeling...
08/17/2022

Disentangled Speaker Representation Learning via Mutual Information Minimization

Domain mismatch problem caused by speaker-unrelated feature has been a m...
04/30/2022

Loss Function Entropy Regularization for Diverse Decision Boundaries

Is it possible to train several classifiers to perform meaningful crowd-...
12/21/2021

Max-Margin Contrastive Learning

Standard contrastive learning approaches usually require a large number ...
04/01/2019

Contrastive Predictive Coding Based Feature for Automatic Speaker Verification

This thesis describes our ongoing work on Contrastive Predictive Coding ...

Code Repositories

contrastive-equilibrium-learning

None


view repo