The ReturnZero System for VoxCeleb Speaker Recognition Challenge 2022
This work addresses speaker recognition for security or biometric applications, but it is incremental as it builds on existing methods from previous challenges.
The paper tackled speaker verification in the VoxCeleb Speaker Recognition Challenge 2022 by fusing multiple models with extra-temporal training and fine-tuning strategies, achieving a final score of 0.165 DCF and 2.912% EER on the test set.
In this paper, we describe the top-scoring submissions for team RTZR VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22) in the closed dataset, speaker verification Track 1. The top performed system is a fusion of 7 models, which contains 3 different types of model architectures. We focus on training models to learn extra-temporal information. Therefore, all models were trained with 4-6 second frames for each utterance. Also, we apply the Large Margin Fine-tuning strategy which has shown good performance on the previous challenges for some of our fusion models. While the evaluation process, we apply the scoring methods with adaptive symmetric normalization (AS-Norm) and matrix score average (MSA). Finally, we mix up models with logistic regression to fuse all the trained models. The final submission achieves 0.165 DCF and 2.912% EER on the VoxSRC22 test set.