You're currently viewing an old version of this dataset. To see the current version, click here.

VoxCeleb

Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings. To address this challenge, a multi-scale feature fusion approach has been proposed to effectively capture speaker characteristics from short utterances.

Data and Resources

This dataset has no data

Cite this as

Arsha Nagrani, Joon Son Chung, Andrew Zisserman (2024). Dataset: VoxCeleb. https://doi.org/10.57702/9zson5bd

Private DOI This DOI is not yet resolvable.
It is available for use in manuscripts, and will be published when the Dataset is made public.

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2310.11004
Citation
  • https://doi.org/10.48550/arXiv.2306.00952
  • https://doi.org/10.48550/arXiv.2211.00511
  • https://doi.org/10.48550/arXiv.2308.14049
  • https://doi.org/10.48550/arXiv.2405.04296
  • https://doi.org/10.48550/arXiv.2401.08415
  • https://doi.org/10.48550/arXiv.2106.06362
  • https://doi.org/10.48550/arXiv.1903.10195
  • https://doi.org/10.48550/arXiv.1810.04826
  • https://doi.org/10.48550/arXiv.1906.08556
  • https://doi.org/10.48550/arXiv.1705.02966
  • https://doi.org/10.48550/arXiv.2207.04834
  • https://doi.org/10.48550/arXiv.2012.08261
  • https://doi.org/10.48550/arXiv.2102.06291
  • https://doi.org/10.48550/arXiv.2005.08781
  • https://doi.org/10.48550/arXiv.2110.02411
  • https://doi.org/10.21437/IberSPEECH.2022-34
  • https://doi.org/10.48550/arXiv.2202.09082
  • https://doi.org/10.48550/arXiv.2401.09146
  • https://doi.org/10.48550/arXiv.1806.08621
Author Arsha Nagrani
More Authors
Joon Son Chung
Andrew Zisserman
Homepage https://www.voxceleb.org/