Build a SRE Challenge System: Lessons from VoxSRC 2022 and CNSRC 2022

TL;DR

This paper discusses building a robust speaker verification challenge system, analyzing various methods based on lessons learned from VoxSRC 2022 and CNSRC 2022 competitions, highlighting effective strategies and system performance.

Contribution

It provides a detailed methodology for constructing strong speaker verification systems and offers comparative analysis of different techniques used in recent challenges.

Findings

Achieved 1st place in CNSRC 2022 speaker verification track.

Achieved 3rd place in VoxSRC 2022 speaker verification track.

Provides insights into effective methods for speaker verification challenges.

Abstract

Many speaker recognition challenges have been held to assess the speaker verification system in the wild and probe the performance limit. Voxceleb Speaker Recognition Challenge (VoxSRC), based on the voxceleb, is the most popular. Besides, another challenge called CN-Celeb Speaker Recognition Challenge (CNSRC) is also held this year, which is based on the Chinese celebrity multi-genre dataset CN-Celeb. This year, our team participated in both speaker verification closed tracks in CNSRC 2022 and VoxSRC 2022, and achieved the 1st place and 3rd place respectively. In most system reports, the authors usually only provide a description of their systems but lack an effective analysis of their methods. In this paper, we will outline how to build a strong speaker verification challenge system and give a detailed analysis of each method compared with some other popular technical means.