A dataset of histograms of original and fake voice recordings (H-Voice)
This paper presents H-Voice, a dataset of 6672 histograms of original and fake voice recordings obtained by the Imitation [1,2] and the Deep Voice [3] methods. The dataset is organized into six directories: Training_fake, Training_original, Validation_fake, Validation_original, External_test1, and E...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-04-01
|
| Series: | Data in Brief |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352340920302250 |