Skip to content
Fan Zeng (Frank)
Back to resources

The LJ Speech Dataset

The LJ Speech Dataset segments one narrator’s readings from public-domain books into English audio and text pairs.

Visit official source (opens in a new tab)

Research use

Use it for reproducible single-speaker synthesis and text preprocessing experiments.

Limitations

Single-speaker audiobook material offers limited evidence about voice diversity. Check the publisher’s territorial rights statement.

License and access

Dataset license
Public domain in the United States (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.