{"url":"/dataset/vocaset","name":"VOCASET","full_name":"VOCASET","description_markdown":"**VOCASET** is a 4D face dataset with about 29 minutes of 4D scans captured at 60 fps and synchronized audio. The dataset has 12 subjects and 480 sequences of about 3-4 seconds each with sentences chosen from an array of standard protocols that maximize phonetic diversity.\r\n\r\nSource: [timzhang642](https://github.com/timzhang642/3D-Machine-Learning#datasets)","description_withheld":null,"homepage":"https://voca.is.tue.mpg.de/","introduced_date":"2019-05-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/capture-learning-and-synthesis-of-3d-speaking","title":"Capture, Learning, and Synthesis of 3D Speaking Styles","first_author":"Daniel Cudeiro","url":null},"license":null,"modalities":[{"name":"3D","url":"/datasets/modality/3d"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"3D Face Animation","url":"/task/3d-face-animation","datasets_with_task":"/datasets/task/3d-face-animation"},{"name":"Talking Face Generation","url":"/task/talking-face-generation","datasets_with_task":"/datasets/task/talking-face-generation"}],"languages":[],"variants":["VOCASET"],"data_loaders":[],"num_papers_in_archive":60,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-face-animation-on-vocaset","task":"3D Face Animation","dataset_variant":"VOCASET","rows":2,"metrics":["Lip Vertex Error"],"first_row_in_archive_order":{"model":"FaceFormer","paper":"/paper/faceformer-speech-driven-3d-facial-animation","metrics":{"Lip Vertex Error":"5.3742"},"code_links":[{"title":"EvelynFan/FaceFormer","url":"https://github.com/EvelynFan/FaceFormer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/faceformer-speech-driven-3d-facial-animation","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers","date":"2021-12-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/meshtalk-3d-face-animation-from-speech-using","title":"MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement","date":"2021-04-16","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":7,"samples_ran":6,"samples_unverified":1,"pointer_only_for_licence":3,"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."}