Skip to content
Fan Zeng (Frank)
Back to resources

VCTK Corpus

VCTK records English speakers with varied accents reading common and speaker-specific material for speech technology research.

Visit official source (opens in a new tab)

Research use

Use held-out speakers to compare accent or speaker transfer in synthesis and related models.

Limitations

The release has defined recording conditions, and some microphone recordings are missing. Report microphone selection and version.

License and access

Dataset license
Open Data Commons Attribution License (opens in a new tab)
Access status
Direct access

Use the publisher’s resource page and check the terms for the files and version you choose.