UIAI System for Short-Duration Speaker Verification Challenge 2020

07/26/2020
by   Md Sahidullah, et al.
Inria
0

In this work, we present the system description of the UIAI entry for the short-duration speaker verification (SdSV) challenge 2020. Our focus is on Task 1 dedicated to text-dependent speaker verification. We investigate different feature extraction and modeling approaches for automatic speaker verification (ASV) and utterance verification (UV). We have also studied different fusion strategies for combining UV and ASV modules. Our primary submission to the challenge is the fusion of seven subsystems which yields a normalized minimum detection cost function (minDCF) of 0.072 and an equal error rate (EER) of 2.14 identification based model with phone-discriminative bottleneck features gives a normalized minDCF of 0.118 and achieves 19 state-of-the-art challenge baseline.

READ FULL TEXT

page 1

page 2

page 3

page 4

12/13/2019

Short-duration Speaker Verification (SdSV) Challenge 2020: the Challenge Evaluation Plan

This document describes task1 of the Short-Duration Speaker Verification...
05/15/2020

On Bottleneck Features for Text-Dependent Speaker Verification Using X-vectors

Applying x-vectors for speaker verification has recently attracted great...
08/03/2022

The SJTU System for Short-duration Speaker Verification Challenge 2021

This paper presents the SJTU system for both text-dependent and text-ind...
08/07/2016

Incorporation of Speech Duration Information in Score Fusion of Speaker Recognition Systems

In recent years identity-vector (i-vector) based speaker verification (S...
01/29/2019

Quality Measures for Speaker Verification with Short Utterances

The performances of the automatic speaker verification (ASV) systems deg...
08/08/2020

NPU Speaker Verification System for INTERSPEECH 2020 Far-Field Speaker Verification Challenge

This paper describes the NPU system submitted to Interspeech 2020 Far-Fi...

Please sign up or login with your details

Forgot password? Click here to reset