{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:V56YWO7YHJOOYFEGAASYKR6YGA","short_pith_number":"pith:V56YWO7Y","schema_version":"1.0","canonical_sha256":"af7d8b3bf83a5cec148600258547d83035945f6e9729549f541fbb2194d1865b","source":{"kind":"arxiv","id":"2007.01216","version":3},"attestation_state":"computed","paper":{"title":"Spot the conversation: speaker diarisation in the wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Arsha Nagrani, Jaesung Huh, Joon Son Chung, Triantafyllos Afouras","submitted_at":"2020-07-02T15:55:54Z","abstract_excerpt":"The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for YouTube videos. Our method consists of active speaker detection using audio-visual methods and speaker verification using self-enrolled speaker models. Second, we integrate our method into a semi-automatic dataset creation pipeline which significantly reduces the number of hours required to annotate videos with diarisation labels. Finally, we use this pipeline to create a large-scale diarisation dataset called VoxCo"},"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":"2007.01216","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-07-02T15:55:54Z","cross_cats_sorted":["cs.CV","eess.AS","eess.IV"],"title_canon_sha256":"aa983cd5fa3ca7e77c9d416f6b9ec436d6d6efccb0f6485069860ad9a5c022ce","abstract_canon_sha256":"3d295843493ba5755c946159eb337ffd76224874de64ee88b6f83dd827f7099e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:43.380810Z","signature_b64":"qAp4fwlpykpWQgvKNGgRuRLQklc+/wt9lv1msu79qGO9vkTpqaa0cztKRMhV8ndT6tnCutEI8X5M1NC8Fyj6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7d8b3bf83a5cec148600258547d83035945f6e9729549f541fbb2194d1865b","last_reissued_at":"2026-07-05T03:05:43.380373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:43.380373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spot the conversation: speaker diarisation in the wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Andrew Zisserman, Arsha Nagrani, Jaesung Huh, Joon Son Chung, Triantafyllos Afouras","submitted_at":"2020-07-02T15:55:54Z","abstract_excerpt":"The goal of this paper is speaker diarisation of videos collected 'in the wild'. We make three key contributions. First, we propose an automatic audio-visual diarisation method for YouTube videos. Our method consists of active speaker detection using audio-visual methods and speaker verification using self-enrolled speaker models. Second, we integrate our method into a semi-automatic dataset creation pipeline which significantly reduces the number of hours required to annotate videos with diarisation labels. Finally, we use this pipeline to create a large-scale diarisation dataset called VoxCo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01216","kind":"arxiv","version":3},"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/2007.01216/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":"2007.01216","created_at":"2026-07-05T03:05:43.380437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01216v3","created_at":"2026-07-05T03:05:43.380437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01216","created_at":"2026-07-05T03:05:43.380437+00:00"},{"alias_kind":"pith_short_12","alias_value":"V56YWO7YHJOO","created_at":"2026-07-05T03:05:43.380437+00:00"},{"alias_kind":"pith_short_16","alias_value":"V56YWO7YHJOOYFEG","created_at":"2026-07-05T03:05:43.380437+00:00"},{"alias_kind":"pith_short_8","alias_value":"V56YWO7Y","created_at":"2026-07-05T03:05:43.380437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA","json":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA.json","graph_json":"https://pith.science/api/pith-number/V56YWO7YHJOOYFEGAASYKR6YGA/graph.json","events_json":"https://pith.science/api/pith-number/V56YWO7YHJOOYFEGAASYKR6YGA/events.json","paper":"https://pith.science/paper/V56YWO7Y"},"agent_actions":{"view_html":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA","download_json":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA.json","view_paper":"https://pith.science/paper/V56YWO7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01216&json=true","fetch_graph":"https://pith.science/api/pith-number/V56YWO7YHJOOYFEGAASYKR6YGA/graph.json","fetch_events":"https://pith.science/api/pith-number/V56YWO7YHJOOYFEGAASYKR6YGA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA/action/storage_attestation","attest_author":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA/action/author_attestation","sign_citation":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA/action/citation_signature","submit_replication":"https://pith.science/pith/V56YWO7YHJOOYFEGAASYKR6YGA/action/replication_record"}},"created_at":"2026-07-05T03:05:43.380437+00:00","updated_at":"2026-07-05T03:05:43.380437+00:00"}