The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge

Weiqing Wang, Danwei Cai, Qingjian Lin, Lin Yang, Junjie Wang, Jin Wang, Ming Li

Abstract

This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4. Our system including a voice activity detection (VAD) model, a speaker embedding model, two clustering-based speaker diarization systems with different similarity measurements, two different overlapped speech detection (OSD) models, and a target-speaker voice activity detection (TS-VAD) model. Our final submission, consisting of 5 independent systems, achieves a DER of 5.07% on the challenge test set.
BibTeX
@misc{wang2021dku,
  author = {Weiqing Wang and Danwei Cai and Qingjian Lin and Lin Yang and Junjie Wang and Jin Wang and Ming Li},
  title = {{The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge}},
  year = {2021},
  eprint = {2109.02002},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2109.02002},
}

Loading related content...

Figure