{"url":"/dataset/deepspeak-dataset-v1-0","name":"DeepSpeak Dataset v1.0","full_name":null,"description_markdown":"The DeepSpeak dataset contains over 43 hours of real and deepfake footage of people talking and gesturing in front of their webcams. The source data was collected from a diverse set of participants in their natural environments and the deepfakes were generated using state-of-the-art open-source lip-sync and face-swap software.","description_withheld":null,"homepage":"https://huggingface.co/datasets/faridlab/deepspeak_v1","introduced_date":"2024-08-09","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"}],"tasks":[{"name":"DeepFake Detection","url":"/task/deepfake-detection","datasets_with_task":"/datasets/task/deepfake-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DeepSpeak Dataset v1.0"],"data_loaders":[],"num_papers_in_archive":0,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}