{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KUJL3JWCULG2JCINLT5HHFBADL","short_pith_number":"pith:KUJL3JWC","schema_version":"1.0","canonical_sha256":"5512bda6c2a2cda4890d5cfa7394201ac629ba5cdcc8c5a855d3028d24a57359","source":{"kind":"arxiv","id":"1806.05622","version":2},"attestation_state":"computed","paper":{"title":"VoxCeleb2: Deep Speaker Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Arsha Nagrani, Joon Son Chung","submitted_at":"2018-06-14T15:59:12Z","abstract_excerpt":"The objective of this paper is speaker recognition under noisy and unconstrained conditions.\n  We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset.\n  Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice u"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1806.05622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-06-14T15:59:12Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"641e6cf348f68cc06249a85cecdb35102619c5cb0d0a8d29bf7d573285c3fca4","abstract_canon_sha256":"79cac224fed53dfc66a7e62d64d47d81804ec4f3b39b3d2a96bed1597cc38209"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:59.770480Z","signature_b64":"ZRdnCO4L4Pkr+er0TX/YsNW+3xemnUq9FVVQpl1i332tVWtXUbjj7h2Nz0ak3AkI6zcU4+mhUt8z8L5izyAmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5512bda6c2a2cda4890d5cfa7394201ac629ba5cdcc8c5a855d3028d24a57359","last_reissued_at":"2026-07-05T01:48:59.770055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:59.770055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxCeleb2: Deep Speaker Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Arsha Nagrani, Joon Son Chung","submitted_at":"2018-06-14T15:59:12Z","abstract_excerpt":"The objective of this paper is speaker recognition under noisy and unconstrained conditions.\n  We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset.\n  Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05622","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1806.05622/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.05622","created_at":"2026-07-05T01:48:59.770115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05622v2","created_at":"2026-07-05T01:48:59.770115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05622","created_at":"2026-07-05T01:48:59.770115+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUJL3JWCULG2","created_at":"2026-07-05T01:48:59.770115+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUJL3JWCULG2JCIN","created_at":"2026-07-05T01:48:59.770115+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUJL3JWC","created_at":"2026-07-05T01:48:59.770115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24336","citing_title":"TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23354","citing_title":"Explainable AI in Speaker Recognition -- Making Latent Representations Understandable","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22901","citing_title":"Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09098","citing_title":"HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08087","citing_title":"Assessing the Energy and Carbon Emissions of Neural Speaker Verification Model in Training and Inference","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08078","citing_title":"On Low-Bit Quantization Errors in Speaker Verification: Diagnostic and Mitigation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01620","citing_title":"Real-Time Generation of Streamable Talking Portrait Video with Reference-Guided Deep Compression VAEs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01031","citing_title":"Temporally-Aligned Evaluation for Audio-Driven Talking Head Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24336","citing_title":"TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30230","citing_title":"IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00751","citing_title":"Head-Pose-Aware Visual Speech Recognition with FiLM Modulation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"1907.06111","citing_title":"Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2408.05366","citing_title":"The DeepSpeak Dataset","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28022","citing_title":"Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23354","citing_title":"Explainable AI in Speaker Recognition -- Making Latent Representations Understandable","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07766","citing_title":"Head Similarity: Modeling Structured Whole-Head Appearance Beyond Face Recognition","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14560","citing_title":"DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15923","citing_title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18326","citing_title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL","json":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL.json","graph_json":"https://pith.science/api/pith-number/KUJL3JWCULG2JCINLT5HHFBADL/graph.json","events_json":"https://pith.science/api/pith-number/KUJL3JWCULG2JCINLT5HHFBADL/events.json","paper":"https://pith.science/paper/KUJL3JWC"},"agent_actions":{"view_html":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL","download_json":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL.json","view_paper":"https://pith.science/paper/KUJL3JWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05622&json=true","fetch_graph":"https://pith.science/api/pith-number/KUJL3JWCULG2JCINLT5HHFBADL/graph.json","fetch_events":"https://pith.science/api/pith-number/KUJL3JWCULG2JCINLT5HHFBADL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL/action/storage_attestation","attest_author":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL/action/author_attestation","sign_citation":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL/action/citation_signature","submit_replication":"https://pith.science/pith/KUJL3JWCULG2JCINLT5HHFBADL/action/replication_record"}},"created_at":"2026-07-05T01:48:59.770115+00:00","updated_at":"2026-07-05T01:48:59.770115+00:00"}