The UPC Speaker Verification System Submitted To Voxceleb Speaker Recognition Challenge 2020 (voxsrc-20)

Abstract

This report describes the submission from Technical University of Catalonia (UPC) to the VoxCeleb Speaker Recognition Challenge (VoxSRC-20) at Interspeech 2020. The final submission is a combination of three systems. System-1 is an autoencoder based approach which tries to reconstruct similar i-vectors, whereas System-2 and -3 are Convolutional Neural Network (CNN) based siamese architectures. The siamese networks have two and three branches, respectively, where each branch is a CNN encoder. The double-branch siamese performs binary classification using cross entropy loss during training. Whereas, our triple-branch siamese is trained to learn speaker embeddings using triplet loss. We provide results of our systems on VoxCeleb-1 test, VoxSRC-20 validation and test sets.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykhan2020the

Related papers

• The Xx205 System 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
• Beijing ZKJ-NPU Speaker Verification System For Voxceleb Speaker Recognition Challenge 2021 (2021)0.00
• The Phonexia Voxceleb Speaker Recognition Challenge 2021 System Description (2021)0.00
• Clova Baseline System For The Voxceleb Speaker Recognition Challenge 2020 (2020)0.00
• Tongji University Undergraduate Team For The Voxceleb Speaker Recognition Challenge2020 (2020)0.00
• The Newsbridge -telecom Sudparis Voxceleb Speaker Recognition Challenge 2022 System Description (2023)0.00