UIAI System for Short-Duration Speaker Verification Challenge 2020
Files
Self archived version
final draftDate
2021Unique identifier
10.1109/SLT48900.2021.9383596Metadata
Show full item recordMore information
Self-archived item
Citation
Sahidullah, Md. Kumar Sarkar, Achintya. Vestman, Ville. Liu, Xuechen. Serizel, Romain. Kinnunen, Tomi. Tan, Zheng-Hua. Vincent, Emmanuel. (2021). UIAI System for Short-Duration Speaker Verification Challenge 2020. 2021 IEEE Spoken Language Technology Workshop (SLT) Proceedings, 323-329. 10.1109/SLT48900.2021.9383596.Rights
Licensed under
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.
