Adaptive Margin Circle Loss for Speaker Verification

06/15/2021
by   Runqiu Xiao, et al.
0

Deep-Neural-Network (DNN) based speaker verification sys-tems use the angular softmax loss with margin penalties toenhance the intra-class compactness of speaker embeddings,which achieved remarkable performance. In this paper, we pro-pose a novel angular loss function called adaptive margin cir-cle loss for speaker verification. The stage-based margin andchunk-based margin are applied to improve the angular discrim-ination of circle loss on the training set. The analysis on gradi-ents shows that, compared with the previous angular loss likeAdditive Margin Softmax(Am-Softmax), circle loss has flexi-ble optimization and definite convergence status. Experimentsare carried out on the Voxceleb and SITW. By applying adap-tive margin circle loss, our best system achieves 1.31

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/18/2021

Real Additive Margin Softmax for Speaker Verification

The additive margin softmax (AM-Softmax) loss has delivered remarkable p...
research
04/06/2019

Large Margin Softmax Loss for Speaker Verification

In neural network based speaker verification, speaker embedding is expec...
research
08/12/2019

A Study on Angular Based Embedding Learning for Text-independent Speaker Verification

Learning a good speaker embedding is important for many automatic speake...
research
06/18/2019

Margin Matters: Towards More Discriminative Deep Neural Network Embeddings for Speaker Recognition

Recently, speaker embeddings extracted from a speaker discriminative dee...
research
12/22/2022

Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and Angular Spaces

The classification loss functions used in deep neural network classifier...
research
11/10/2019

Improved Large-margin Softmax Loss for Speaker Diarisation

Speaker diarisation systems nowadays use embeddings generated from speec...
research
05/06/2022

Norm-Scaling for Out-of-Distribution Detection

Out-of-Distribution (OoD) inputs are examples that do not belong to the ...

Please sign up or login with your details

Forgot password? Click here to reset