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...

Descripción completa

Detalles Bibliográficos
Autores principales: Ballesteros, Dora M., Rodriguez, Yohanna, Renza, Diego
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2020
Materias:
Computer Science
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7058910/
https://www.ncbi.nlm.nih.gov/pubmed/32154354
http://dx.doi.org/10.1016/j.dib.2020.105331

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7058910/
https://www.ncbi.nlm.nih.gov/pubmed/32154354
http://dx.doi.org/10.1016/j.dib.2020.105331

Ejemplares similares