UTD-CRSS Systems For 2016 NIST Speaker Recognition Evaluation

Abstract

This document briefly describes the systems submitted by the Center for Robust Speech Systems (CRSS) from The University of Texas at Dallas (UTD) to the 2016 National Institute of Standards and Technology (NIST) Speaker Recognition Evaluation (SRE). We developed several UBM and DNN i-Vector based speaker recognition systems with different data sets and feature representations. Given that the emphasis of the NIST SRE 2016 is on language mismatch between training and enrollment/test data, so-called domain mismatch, in our system development we focused on: (1) using unlabeled in-domain data for centralizing data to alleviate the domain mismatch problem, (2) finding the best data set for training LDA/PLDA, (3) using newly proposed dimension reduction technique incorporating unlabeled in-domain data before PLDA training, (4) unsupervised speaker clustering of unlabeled data and using them alone or with previous SREs for PLDA training, (5) score calibration using only unlabeled data and comb

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2016utd

Related papers

• KU-ISPL Speaker Recognition Systems Under Language Mismatch Condition For NIST 2016 Speaker Recognition Evaluation (2017)0.00
• LIA System Description For NIST SRE 2016 (2016)0.00
• HLT-NUS Submission For NIST 2019 Multimedia Speaker Recognition Evaluation (2020)0.00
• The Intelligent Voice 2016 Speaker Recognition System (2016)0.00
• The IBM Speaker Recognition System: Recent Advances And Error Analysis (2016)8.60
• STC Speaker Recognition Systems For The Voices From A Distance Challenge (2019)7.81
• I4U Submission To NIST SRE 2018: Leveraging From A Decade Of Shared Experiences (2019)0.00
• NIST SRE CTS Superset: A Large-scale Dataset For Telephony Speaker Recognition (2021)0.00