# SJTU-AISPEECH System for VoxCeleb Speaker Recognition Challenge 2022

arXiv: https://arxiv.org/abs/2209.09076 · HTML: https://mlsanity.com/paper/2209.09076/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2022.

## Built on by (most cited first, 6 of 6)

- [VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge](https://mlsanity.com/paper/2302.10248/) (2023)
- [A Teacher-Student approach for extracting informative speaker embeddings from speech mixtures](https://mlsanity.com/paper/2306.00634/) (2023)
- [Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification](https://mlsanity.com/paper/2305.12703/) (2023)
- [ChinaTelecom System Description to VoxCeleb Speaker Recognition Challenge 2023](https://mlsanity.com/paper/2308.08181/) (2023)
- [Memory-Efficient Training for Text-Dependent SV with Independent Pre-trained Models](https://mlsanity.com/paper/2411.10828/) (2024)
- [Memory-Efficient Training for Deep Speaker Embedding Learning in Speaker Verification](https://mlsanity.com/paper/2412.01195/) (2024)

## Abstract (arXiv)

This report describes the SJTU-AISPEECH system for the Voxceleb Speaker Recognition Challenge 2022. For track1, we implemented two kinds of systems, the online system and the offline system. Different ResNet-based backbones and loss functions are explored. Our final fusion system achieved 3rd place in track1. For track3, we implemented statistic adaptation and jointly training based domain adaptation. In the jointly training based domain adaptation, we jointly trained the source and target domain dataset with different training objectives to do the domain adaptation. We explored two different training objectives for target domain data, self-supervised learning based angular proto-typical loss and semi-supervised learning based classification loss with estimated pseudo labels. Besides, we used the dynamic loss-gate and label correction (DLG-LC) strategy to improve the quality of pseudo labels when the target domain objective is a classification loss. Our final fusion system achieved 4th place (very close to 3rd place, relatively less than 1%) in track3.