Beijing ZKJ-NPU Speaker Verification System For Voxceleb Speaker Recognition Challenge 2021

Abstract

In this report, we describe the Beijing ZKJ-NPU team submission to the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). We participated in the fully supervised speaker verification track 1 and track 2. In the challenge, we explored various kinds of advanced neural network structures with different pooling layers and objective loss functions. In addition, we introduced the ResNet-DTCF, CoAtNet and PyConv networks to advance the performance of CNN-based speaker embedding model. Moreover, we applied embedding normalization and score normalization at the evaluation stage. By fusing 11 and 14 systems, our final best performances (minDCF/EER) on the evaluation trails are 0.1205/2.8160% and 0.1175/2.8400% respectively for track 1 and 2. With our submission, we came to the second place in the challenge for both tracks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2021beijing

Related papers

• Tongji University Undergraduate Team For The Voxceleb Speaker Recognition Challenge2020 (2020)0.00
• The Xx205 System For The Voxceleb Speaker Recognition Challenge 2020 (2020)0.00
• Tongji University Team For The Voxceleb Speaker Recognition Challenge 2020 (2020)0.00
• The Kriston AI System For The Voxceleb Speaker Recognition Challenge 2022 (2022)0.00
• The DKU-MSXF Speaker Verification System For The Voxceleb Speaker Recognition Challenge 2023 (2023)0.00
• The Phonexia Voxceleb Speaker Recognition Challenge 2021 System Description (2021)0.00
• The SJTU X-LANCE Lab System For CNSRC 2022 (2022)6.22
• The Dku-dukeece System For The Self-supervision Speaker Verification Task Of The 2021 Voxceleb Speaker Recognition Challenge (2021)0.00