{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/voxceleb2","name":"VoxCeleb2","full_name":"VoxCeleb2","description_markdown":"**VoxCeleb2** is a large scale speaker recognition dataset obtained automatically from open-source media. VoxCeleb2 consists of over a million utterances from over 6k speakers. Since the dataset is collected ‘in the wild’, the speech segments are corrupted with real world noise including laughter, cross-talk, channel effects, music and other sounds. The dataset is also multilingual, with speech from speakers of 145 different nationalities, covering a wide range of accents, ages, ethnicities and languages. The dataset is audio-visual, so is also useful for a number of other applications, for example – visual speech synthesis, speech separation, cross-modal transfer from face to voice or vice versa and training face recognition from video to complement existing face recognition datasets.\r\n\r\nSource: [VoxCeleb2: Deep Speaker Recognition](https://arxiv.org/pdf/1806.05622v2.pdf)\r\nImage Source: [https://www.robots.ox.ac.uk/~vgg/data/voxceleb/](https://www.robots.ox.ac.uk/~vgg/data/voxceleb/)","description_withheld":null,"homepage":"https://www.robots.ox.ac.uk/~vgg/data/voxceleb/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/voxceleb2-deep-speaker-recognition","title":"VoxCeleb2: Deep Speaker Recognition","first_author":"Joon Son Chung","url":null},"license":{"name":"CC BY 4.0","url":"https://www.robots.ox.ac.uk/~vgg/data/voxceleb/files/license.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Speech Separation","url":"/task/speech-separation","datasets_with_task":"/datasets/task/speech-separation"},{"name":"Speaker Verification","url":"/task/speaker-verification","datasets_with_task":"/datasets/task/speaker-verification"},{"name":"Talking Head Generation","url":"/task/talking-head-generation","datasets_with_task":"/datasets/task/talking-head-generation"}],"languages":[{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["VoxCeleb2 - 1-shot learning","VoxCeleb2 - 8-shot learning","VoxCeleb2 - 32-shot learning","VoxCeleb2"],"data_loaders":[],"num_papers_in_archive":564,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-separation-on-voxceleb2","task":"Speech Separation","dataset_variant":"VoxCeleb2","rows":5,"metrics":["SI-SNRi","SDRi"],"first_row_in_archive_order":{"model":"IIANet","paper":"/paper/scanet-a-self-and-cross-attention-network-for","metrics":{"SDRi":"15.1","SI-SNRi":"14.0"},"code_links":[{"title":"JusperLee/IIANet","url":"https://github.com/JusperLee/IIANet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-1-shot","task":"Talking Head Generation","dataset_variant":"VoxCeleb2 - 1-shot learning","rows":5,"metrics":["CSIM","LPIPS","Normalized Pose Error","SSIM","inference time (ms)","FID"],"first_row_in_archive_order":{"model":"Fast Bi-layer Avatars (medium size)","paper":"/paper/fast-bi-layer-neural-synthesis-of-one-shot","metrics":{"CSIM":"0.653","LPIPS":"0.358","Normalized Pose Error":"43.3","SSIM":"0.508","inference time (ms)":"4"},"code_links":[{"title":"saic-violet/bilayer-model","url":"https://github.com/saic-violet/bilayer-model"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-8-shot","task":"Talking Head Generation","dataset_variant":"VoxCeleb2 - 8-shot learning","rows":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"CainGAN","paper":"/paper/pose-manipulation-with-identity-preservation-1","metrics":{"FID":"24.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/speaker-verification-on-voxceleb2","task":"Speaker Verification","dataset_variant":"VoxCeleb2","rows":1,"metrics":["EER"],"first_row_in_archive_order":{"model":"ResNet-50","paper":"/paper/voxceleb2-deep-speaker-recognition","metrics":{"EER":"100"},"code_links":[{"title":"a-nagrani/VGGVox","url":"https://github.com/a-nagrani/VGGVox"},{"title":"MainRo/deep-speaker","url":"https://github.com/MainRo/deep-speaker"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/talking-head-generation-on-voxceleb2-32-shot","task":"Talking Head Generation","dataset_variant":"VoxCeleb2 - 32-shot learning","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"Few-shot Adversarial Model","paper":"/paper/few-shot-adversarial-learning-of-realistic","metrics":{"FID":"30.6"},"code_links":[{"title":"vincent-thevenin/Realistic-Neural-Talking-Head-Models","url":"https://github.com/vincent-thevenin/Realistic-Neural-Talking-Head-Models"},{"title":"grey-eye/talking-heads","url":"https://github.com/grey-eye/talking-heads"},{"title":"shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap","url":"https://github.com/shoutOutYangJie/Few-Shot-Adversarial-Learning-for-face-swap"},{"title":"ZVK/Talking-Heads","url":"https://github.com/ZVK/Talking-Heads"},{"title":"ZVK/talking_heads","url":"https://github.com/ZVK/talking_heads"},{"title":"Ierezell/PapierFewShot","url":"https://github.com/Ierezell/PapierFewShot"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":6,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":7,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/rtfs-net-recurrent-time-frequency-modelling","slug":"rtfs-net-recurrent-time-frequency-modelling","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","date":"2023-09-29","arxiv_id":"2309.17189","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["spkgyk/RTFS-Net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rtfs-net-recurrent-time-frequency-modelling#ran","syntology_url":"https://syntology.ai/paper/2309.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17189"}}}},{"paper":"/paper/scanet-a-self-and-cross-attention-network-for","slug":"scanet-a-self-and-cross-attention-network-for","title":"IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation","date":"2023-08-16","arxiv_id":"2308.08143","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["JusperLee/IIANet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scanet-a-self-and-cross-attention-network-for#ran","syntology_url":"https://syntology.ai/paper/2308.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08143"}}}},{"paper":"/paper/an-audio-visual-speech-separation-model","slug":"an-audio-visual-speech-separation-model","title":"An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits","date":"2022-12-21","arxiv_id":"2212.10744","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jusperlee/ctcnet","jusperlee/lrs3-for-speech-separation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-audio-visual-speech-separation-model#ran","syntology_url":"https://syntology.ai/paper/2212.10744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10744"}}}},{"paper":"/paper/fast-bi-layer-neural-synthesis-of-one-shot","slug":"fast-bi-layer-neural-synthesis-of-one-shot","title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","date":"2020-08-24","arxiv_id":"2008.10174","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/pose-manipulation-with-identity-preservation-1","slug":"pose-manipulation-with-identity-preservation-1","title":"Pose Manipulation with Identity Preservation","date":"2020-04-20","arxiv_id":"2004.09169","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/few-shot-adversarial-learning-of-realistic","slug":"few-shot-adversarial-learning-of-realistic","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","date":"2019-05-20","arxiv_id":"1905.08233","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}}}},{"paper":"/paper/voxceleb2-deep-speaker-recognition","slug":"voxceleb2-deep-speaker-recognition","title":"VoxCeleb2: Deep Speaker Recognition","date":"2018-06-14","arxiv_id":"1806.05622","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/voxceleb2-deep-speaker-recognition#ran","syntology_url":"https://syntology.ai/paper/1806.05622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05622"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/rtfs-net-recurrent-time-frequency-modelling","slug":"rtfs-net-recurrent-time-frequency-modelling","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","date":"2023-09-29","arxiv_id":"2309.17189","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["spkgyk/RTFS-Net"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rtfs-net-recurrent-time-frequency-modelling#ran","syntology_url":"https://syntology.ai/paper/2309.17189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17189"}}}},{"paper":"/paper/scanet-a-self-and-cross-attention-network-for","slug":"scanet-a-self-and-cross-attention-network-for","title":"IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation","date":"2023-08-16","arxiv_id":"2308.08143","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["JusperLee/IIANet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/scanet-a-self-and-cross-attention-network-for#ran","syntology_url":"https://syntology.ai/paper/2308.08143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08143"}}}},{"paper":"/paper/an-audio-visual-speech-separation-model","slug":"an-audio-visual-speech-separation-model","title":"An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits","date":"2022-12-21","arxiv_id":"2212.10744","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jusperlee/ctcnet","jusperlee/lrs3-for-speech-separation"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/an-audio-visual-speech-separation-model#ran","syntology_url":"https://syntology.ai/paper/2212.10744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10744"}}}},{"paper":"/paper/fast-bi-layer-neural-synthesis-of-one-shot","slug":"fast-bi-layer-neural-synthesis-of-one-shot","title":"Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatars","date":"2020-08-24","arxiv_id":"2008.10174","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/pose-manipulation-with-identity-preservation-1","slug":"pose-manipulation-with-identity-preservation-1","title":"Pose Manipulation with Identity Preservation","date":"2020-04-20","arxiv_id":"2004.09169","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/few-shot-adversarial-learning-of-realistic","slug":"few-shot-adversarial-learning-of-realistic","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","date":"2019-05-20","arxiv_id":"1905.08233","rows_on_this_dataset":3,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/few-shot-adversarial-learning-of-realistic#ran","syntology_url":"https://syntology.ai/paper/1905.08233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.08233"}}}},{"paper":"/paper/voxceleb2-deep-speaker-recognition","slug":"voxceleb2-deep-speaker-recognition","title":"VoxCeleb2: Deep Speaker Recognition","date":"2018-06-14","arxiv_id":"1806.05622","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/voxceleb2-deep-speaker-recognition#ran","syntology_url":"https://syntology.ai/paper/1806.05622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05622"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/voxceleb2/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/voxceleb2/papers/ran/1","json":"/dataset/voxceleb2/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":5,"samples_harvested":20,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":3,"papers_where_every_run_was_an_instrument_failure":1,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"6a595e5d0b2e0976e384252cd2e5844ab6147cfe3faba855473bdca1b92a40b3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}