The SpeakIn System Description for CNSRC2022

TL;DR

This paper describes a speaker verification system developed for CNSRC 2022, utilizing multiple neural architectures and advanced pooling and scoring techniques, achieving top rankings in several challenge tasks.

Contribution

The report introduces a multi-architecture speaker verification system with novel pooling and fine-tuning strategies that significantly improve performance in the CNSRC 2022 challenge.

Findings

Achieved 1st place in open track of SV task

Secured 2nd place in fixed track of SV task

Placed 3rd in SR task

Abstract

This report describes our speaker verification systems for the tasks of the CN-Celeb Speaker Recognition Challenge 2022 (CNSRC 2022). This challenge includes two tasks, namely speaker verification(SV) and speaker retrieval(SR). The SV task involves two tracks: fixed track and open track. In the fixed track, we only used CN-Celeb.T as the training set. For the open track of the SV task and SR task, we added our open-source audio data. The ResNet-based, RepVGG-based, and TDNN-based architectures were developed for this challenge. Global statistic pooling structure and MQMHA pooling structure were used to aggregate the frame-level features across time to obtain utterance-level representation. We adopted AM-Softmax and AAM-Softmax combined with the Sub-Center method to classify the resulting embeddings. We also used the Large-Margin Fine-Tuning strategy to further improve the model performance. In the backend, Sub-Mean and AS-Norm were used. In the SV task fixed track, our system was a fusion of five models, and two models were fused in the SV task open track. And we used a single system in the SR task. Our approach leads to superior performance and comes the 1st place in the open track of the SV task, the 2nd place in the fixed track of the SV task, and the 3rd place in the SR task.