English

The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description

Audio and Speech Processing 2023-08-22 v2

Abstract

This report describes ID R&D team submissions for Track 2 (open) to the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our solution is based on the fusion of deep ResNets and self-supervised learning (SSL) based models trained on a mixture of a VoxCeleb2 dataset and a large version of a VoxTube dataset. The final submission to the Track 2 achieved the first place on the VoxSRC-23 public leaderboard with a minDCF(0.05) of 0.0762 and EER of 1.30%.

Keywords

Cite

@article{arxiv.2308.08294,
  title  = {The ID R&D VoxCeleb Speaker Recognition Challenge 2023 System Description},
  author = {Nikita Torgashov and Rostislav Makarov and Ivan Yakovlev and Pavel Malov and Andrei Balykin and Anton Okhotnikov},
  journal= {arXiv preprint arXiv:2308.08294},
  year   = {2023}
}