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

VCTK

Voice conversion (VC) is a technique that alters the voice of a source speaker to a target style, such as speaker identity, prosody, and emotion, while keeping the linguistic content unchanged.

Data and Resources

This dataset has no data

Cite this as

Jennifer Williams, Karla Pizzi, Paul-Gauthier Noé, Sneha Das (2024). Dataset: VCTK. https://doi.org/10.57702/gtivj7m0

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.2407.12707
Citation
  • https://doi.org/10.48550/arXiv.2104.09995
  • https://doi.org/10.48550/arXiv.1905.05879
  • https://doi.org/10.48550/arXiv.2104.00931
  • https://doi.org/10.48550/arXiv.2203.00648
  • https://doi.org/10.48550/arXiv.1810.04826
  • https://doi.org/10.48550/arXiv.2205.15370
  • https://doi.org/10.48550/arXiv.2210.15418
Author Jennifer Williams
More Authors
Karla Pizzi
Paul-Gauthier Noé
Sneha Das
Homepage https://www.kaggle.com/c/vctk