Query Expansion System for the VoxCeleb Speaker Recognition Challenge 2020

11/04/2020
by   Yu-Sen Cheng, et al.
0

In this report, we describe our submission to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020. Two approaches are adopted. One is to apply query expansion on speaker verification, which shows significant progress compared to baseline in the study. Another is to use Kaldi extract x-vector and to combine its Probabilistic Linear Discriminant Analysis (PLDA) score with ResNet score.

READ FULL TEXT

page 1

page 2

research
05/22/2023

The HCCL system for VoxCeleb Speaker Recognition Challenge 2022

This report describes our submission to track1 and track3 for VoxCeleb S...
research
11/03/2020

ShaneRun System Description to VoxCeleb Speaker Recognition Challenge 2020

In this report, we describe the submission of ShaneRun's team to the Vox...
research
03/18/2015

Shared latent subspace modelling within Gaussian-Binary Restricted Boltzmann Machines for NIST i-Vector Challenge 2014

This paper presents a novel approach to speaker subspace modelling based...
research
08/16/2023

ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023

This technical report describes ChinaTelecom system for Track 1 (closed)...
research
09/29/2020

Clova Baseline System for the VoxCeleb Speaker Recognition Challenge 2020

This report describes our submission to the VoxCeleb Speaker Recognition...
research
10/10/2020

Remarks on Optimal Scores for Speaker Recognition

In this article, we first establish the theory of optimal scores for spe...
research
11/24/2021

A Study on Decoupled Probabilistic Linear Discriminant Analysis

Probabilistic linear discriminant analysis (PLDA) has broad application ...

Please sign up or login with your details

Forgot password? Click here to reset