UIAI System for Short-Duration Speaker Verification Challenge 2020 - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

UIAI System for Short-Duration Speaker Verification Challenge 2020

Abstract

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% on the evaluation set. The single system consisting of a pass-phrase identification based model with phone-discriminative bottleneck features gives a normalized minDCF of 0.118 and achieves 19% relative improvement over the state-of-the-art challenge baseline.
Fichier principal
Vignette du fichier
IEEE_SLT2021_Final.pdf (529.25 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02907037 , version 1 (27-07-2020)
hal-02907037 , version 2 (10-12-2020)

Identifiers

Cite

Md Sahidullah, Achintya Kumar Sarkar, Ville Vestman, Xuechen Liu, Romain Serizel, et al.. UIAI System for Short-Duration Speaker Verification Challenge 2020. SLT 2021 - IEEE Spoken Language Technology Workshop, IEEE, Jan 2021, Shenzhen / Virtual, China. ⟨10.1109/SLT48900.2021.9383596⟩. ⟨hal-02907037v2⟩
190 View
302 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More