{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/voxceleb2-deep-speaker-recognition","title":"VoxCeleb2: Deep Speaker Recognition","arxiv_id":"1806.05622","date":"2018-06-14","proceeding":null,"authors":["Joon Son Chung","Arsha Nagrani","Andrew Zisserman"],"abstract":"The objective of this paper is speaker recognition under noisy and\nunconstrained conditions.\n  We make two key contributions. First, we introduce a very large-scale\naudio-visual speaker recognition dataset collected from open-source media.\nUsing a fully automated pipeline, we curate VoxCeleb2 which contains over a\nmillion utterances from over 6,000 speakers. This is several times larger than\nany publicly available speaker recognition dataset.\n  Second, we develop and compare Convolutional Neural Network (CNN) models and\ntraining strategies that can effectively recognise identities from voice under\nvarious conditions. The models trained on the VoxCeleb2 dataset surpass the\nperformance of previous works on a benchmark dataset by a significant margin.","url_abs":"http://arxiv.org/abs/1806.05622v2","url_pdf":"http://arxiv.org/pdf/1806.05622v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"voxceleb2-deep-speaker-recognition","repo_url":"https://github.com/MainRo/deep-speaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"voxceleb2-deep-speaker-recognition","repo_url":"https://github.com/a-nagrani/VGGVox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"}],"methods":[],"datasets_introduced":[{"slug":"voxceleb2","name":"VoxCeleb2","full_name":"VoxCeleb2"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/speaker-verification-on-voxceleb2","task":"Speaker Verification","dataset":"VoxCeleb2","model":"ResNet-50","rank_in_archive_order":1,"of":1,"metrics":{"EER":"100"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/1806.05622","atlas_url":"https://app.syntology.ai/?focus=1806.05622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05622"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/a-nagrani/VGGVox","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MainRo/deep-speaker","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":13},"by_repo_kind":{"listed":{"samples":13,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"acad88e22e1a95fa","entry":"data_to_feature","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/feature/process_path.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/feature/process_path.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"acad88e22e1a95fa"}},{"code_sha256_prefix":"41b8c9dc07ab681e","entry":"encode_wav","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/toolbox/audio_codec.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/toolbox/audio_codec.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"41b8c9dc07ab681e"}},{"code_sha256_prefix":"7a4d33736c2bab3f","entry":"filter_banks","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/toolbox/audio_features.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/toolbox/audio_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7a4d33736c2bab3f"}},{"code_sha256_prefix":"3bbf8d73f6b7970c","entry":"frame","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/toolbox/audio_features.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/toolbox/audio_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bbf8d73f6b7970c"}},{"code_sha256_prefix":"b67cc2f8cbc8028c","entry":"label_from_path","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/features.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b67cc2f8cbc8028c"}},{"code_sha256_prefix":"5fba08d946360f95","entry":"label_from_path","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/feature/compute_features.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/feature/compute_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5fba08d946360f95"}},{"code_sha256_prefix":"3f53794c7b744cb9","entry":"label_to_array","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/do_train.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/do_train.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f53794c7b744cb9"}},{"code_sha256_prefix":"5a2d157cd88068dc","entry":"load_config","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/do_train.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/do_train.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a2d157cd88068dc"}},{"code_sha256_prefix":"bf4c61f4b6dbb9ef","entry":"pair_set","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/dataset/split.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/dataset/split.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf4c61f4b6dbb9ef"}},{"code_sha256_prefix":"26a39077504904a5","entry":"pre_emphasis","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/toolbox/audio_features.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/toolbox/audio_features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"26a39077504904a5"}},{"code_sha256_prefix":"5e35f05a037f77e5","entry":"set_from_path","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/features.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/features.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e35f05a037f77e5"}},{"code_sha256_prefix":"d8b37c1936f3d813","entry":"test_dev_split","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/dataset/split.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/dataset/split.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d8b37c1936f3d813"}},{"code_sha256_prefix":"53db4ef1685b7e80","entry":"train_test_split","repo":"MainRo/deep-speaker","repo_kind":"listed","path":"deep_speaker/dataset/split.py","file_url":"https://github.com/MainRo/deep-speaker/blob/HEAD/deep_speaker/dataset/split.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53db4ef1685b7e80"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}