Skip to content
Fan Zeng (Frank)
Back to resources

Expresso — Read Speech

Studio recordings cover expressive English reading styles including speech delivered softly, rapidly or with laughter.

Visit official source (opens in a new tab)

Research use

Compare recognition accuracy across delivery styles while keeping the corpus and speakers fixed.

Limitations

The read configuration represents four speakers and includes some singing entries. The project’s improvised dialogue does not have the same transcript coverage.

License and access

Dataset license
CC BY-NC 4.0 (opens in a new tab)
Access status
Direct access

Use the read configuration and its text field. Select spoken styles for a speech-only evaluation.

Additional sources