{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6VYRUVS4IF2MIY6SPR6XB7OJYX","short_pith_number":"pith:6VYRUVS4","schema_version":"1.0","canonical_sha256":"f5711a565c4174c463d27c7d70fdc9c5ca53d3a984853155a66f60a70e6c76b9","source":{"kind":"arxiv","id":"1706.08612","version":2},"attestation_state":"computed","paper":{"title":"VoxCeleb: a large-scale speaker identification dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Arsha Nagrani, Joon Son Chung","submitted_at":"2017-06-26T21:42:27Z","abstract_excerpt":"Most existing datasets for speaker identification contain samples obtained under quite constrained conditions, and are usually hand-annotated, hence limited in size. The goal of this paper is to generate a large scale text-independent speaker identification dataset collected 'in the wild'. We make two contributions. First, we propose a fully automated pipeline based on computer vision techniques to create the dataset from open-source media. Our pipeline involves obtaining videos from YouTube; performing active speaker verification using a two-stream synchronization Convolutional Neural Network"},"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":"1706.08612","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-06-26T21:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"a3a675c135cfad53ebd354f1b0c19edb89eef288ddfe4846e801fad579182fa1","abstract_canon_sha256":"4f637327792b03045ec3d7f5d28ea10c4440005b41ee8bf7df43dc4b950c9bde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:59.483560Z","signature_b64":"hNxb8uhJyJC/2bI0pQx/bTar77UmmCq9wLenu18vMHWtjYXk76PvXyCJcKbEI4WkVnMka2OCfIjwlYTFE121Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5711a565c4174c463d27c7d70fdc9c5ca53d3a984853155a66f60a70e6c76b9","last_reissued_at":"2026-07-05T01:48:59.483089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:59.483089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxCeleb: a large-scale speaker identification dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Arsha Nagrani, Joon Son Chung","submitted_at":"2017-06-26T21:42:27Z","abstract_excerpt":"Most existing datasets for speaker identification contain samples obtained under quite constrained conditions, and are usually hand-annotated, hence limited in size. The goal of this paper is to generate a large scale text-independent speaker identification dataset collected 'in the wild'. We make two contributions. First, we propose a fully automated pipeline based on computer vision techniques to create the dataset from open-source media. Our pipeline involves obtaining videos from YouTube; performing active speaker verification using a two-stream synchronization Convolutional Neural Network"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08612","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/1706.08612/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":"1706.08612","created_at":"2026-07-05T01:48:59.483150+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.08612v2","created_at":"2026-07-05T01:48:59.483150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08612","created_at":"2026-07-05T01:48:59.483150+00:00"},{"alias_kind":"pith_short_12","alias_value":"6VYRUVS4IF2M","created_at":"2026-07-05T01:48:59.483150+00:00"},{"alias_kind":"pith_short_16","alias_value":"6VYRUVS4IF2MIY6S","created_at":"2026-07-05T01:48:59.483150+00:00"},{"alias_kind":"pith_short_8","alias_value":"6VYRUVS4","created_at":"2026-07-05T01:48:59.483150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07907","citing_title":"Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks","ref_index":186,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08111","citing_title":"PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23354","citing_title":"Explainable AI in Speaker Recognition -- Making Latent Representations Understandable","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22901","citing_title":"Explainable AI in Speaker Recognition -- Attention Map Visualisation and Evaluation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26144","citing_title":"Neural Speaker Diarization via Multilingual Training: Evaluation on Low-Resource Nepali-Hindi Speech","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21305","citing_title":"LISE : Listenable Interpretable Speaker Embeddings","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18156","citing_title":"ReAge3D: Re-Aging 3D Faces with View Consistency","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09639","citing_title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07063","citing_title":"Beyond Universality: The GCC-FER Dataset and Culture-Aware Adaptation for Dynamic Facial Expression Recognition","ref_index":2,"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":39,"is_internal_anchor":false},{"citing_arxiv_id":"2408.05366","citing_title":"The DeepSpeak Dataset","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03484","citing_title":"Dementia classification from spontaneous speech using wrapper-based feature selection","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15984","citing_title":"Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26327","citing_title":"Dual-LoRA: Parameter-Efficient Adversarial Disentanglement for Cross-Lingual Speaker Verification","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23354","citing_title":"Explainable AI in Speaker Recognition -- Making Latent Representations Understandable","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24794","citing_title":"V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06702","citing_title":"ULTRAS -- Unified Learning of Transformer Representations for Audio and Speech Signals","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16749","citing_title":"ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02990","citing_title":"ChaRVoC: A Challenge-Response Voice Cancelable Authentication System","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX","json":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX.json","graph_json":"https://pith.science/api/pith-number/6VYRUVS4IF2MIY6SPR6XB7OJYX/graph.json","events_json":"https://pith.science/api/pith-number/6VYRUVS4IF2MIY6SPR6XB7OJYX/events.json","paper":"https://pith.science/paper/6VYRUVS4"},"agent_actions":{"view_html":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX","download_json":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX.json","view_paper":"https://pith.science/paper/6VYRUVS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.08612&json=true","fetch_graph":"https://pith.science/api/pith-number/6VYRUVS4IF2MIY6SPR6XB7OJYX/graph.json","fetch_events":"https://pith.science/api/pith-number/6VYRUVS4IF2MIY6SPR6XB7OJYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX/action/storage_attestation","attest_author":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX/action/author_attestation","sign_citation":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX/action/citation_signature","submit_replication":"https://pith.science/pith/6VYRUVS4IF2MIY6SPR6XB7OJYX/action/replication_record"}},"created_at":"2026-07-05T01:48:59.483150+00:00","updated_at":"2026-07-05T01:48:59.483150+00:00"}