LAV-DF Multimodal DeepFake Audio-Visual Dataset

LAV-DF is a multimodal (video tampering and audio tampering) dataset derived from the VoxCeleb2 dataset, containing 136,304 videos, including 36,431 real videos and 99,873 fake videos.

The dataset was released in 2022 by researchers from Monash University, Curtin University and Indian Institute of Technology Ropar.Do You Really Mean That? Content Driven Audio-Visual Deepfake Dataset and Multimodal Method for Temporal Forgery Localization " and journal articles accepted by CVIU "Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization "

By using this dataset, you agree to thisTerms.