{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NIWJHI77DI2WZO5R3JYCIYIH57","short_pith_number":"pith:NIWJHI77","schema_version":"1.0","canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","source":{"kind":"arxiv","id":"1906.10042","version":1},"attestation_state":"computed","paper":{"title":"Who said that?: Audio-visual speaker diarisation of real-world meetings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bong-Jin Lee, Icksang Han, Joon Son Chung","submitted_at":"2019-06-24T16:06:13Z","abstract_excerpt":"The goal of this work is to determine 'who spoke when' in real-world meetings. The method takes surround-view video and single or multi-channel audio as inputs, and generates robust diarisation outputs. To achieve this, we propose a novel iterative approach that first enrolls speaker models using audio-visual correspondence, then uses the enrolled models together with the visual information to determine the active speaker. We show strong quantitative and qualitative performance on a dataset of real-world meetings. The method is also evaluated on the public AMI meeting corpus, on which we demon"},"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":"1906.10042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-06-24T16:06:13Z","cross_cats_sorted":["cs.CV","eess.AS"],"title_canon_sha256":"4a4d362ce3f768983dcb35cc3e6ac2f5c9c6fa0928b6ba7af91f841f9e72198c","abstract_canon_sha256":"b022a3c6b5b4b7d2dbbe296259ca4103f36a26e72d9dac1a1dd5b891f1124438"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:35.642085Z","signature_b64":"BgRB2MIkFE7490FaXvoZaKl7dR3Q3RWnzuzlY0nORPfYs6+oZ+ZBzEC4MNUtB1Ndcye5hT+3l8duGx3YmmL7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2c93a3ff1a356cbbb1da70246107effd1b915f9aff78533c03129d88317dff","last_reissued_at":"2026-05-17T23:42:35.641424Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:35.641424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who said that?: Audio-visual speaker diarisation of real-world meetings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bong-Jin Lee, Icksang Han, Joon Son Chung","submitted_at":"2019-06-24T16:06:13Z","abstract_excerpt":"The goal of this work is to determine 'who spoke when' in real-world meetings. The method takes surround-view video and single or multi-channel audio as inputs, and generates robust diarisation outputs. To achieve this, we propose a novel iterative approach that first enrolls speaker models using audio-visual correspondence, then uses the enrolled models together with the visual information to determine the active speaker. We show strong quantitative and qualitative performance on a dataset of real-world meetings. The method is also evaluated on the public AMI meeting corpus, on which we demon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10042","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1906.10042","created_at":"2026-05-17T23:42:35.641527+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.10042v1","created_at":"2026-05-17T23:42:35.641527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10042","created_at":"2026-05-17T23:42:35.641527+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIWJHI77DI2W","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIWJHI77DI2WZO5R","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIWJHI77","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.10042","citing_title":"Who said that?: Audio-visual speaker diarisation of real-world meetings","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57","json":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57.json","graph_json":"https://pith.science/api/pith-number/NIWJHI77DI2WZO5R3JYCIYIH57/graph.json","events_json":"https://pith.science/api/pith-number/NIWJHI77DI2WZO5R3JYCIYIH57/events.json","paper":"https://pith.science/paper/NIWJHI77"},"agent_actions":{"view_html":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57","download_json":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57.json","view_paper":"https://pith.science/paper/NIWJHI77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.10042&json=true","fetch_graph":"https://pith.science/api/pith-number/NIWJHI77DI2WZO5R3JYCIYIH57/graph.json","fetch_events":"https://pith.science/api/pith-number/NIWJHI77DI2WZO5R3JYCIYIH57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/action/storage_attestation","attest_author":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/action/author_attestation","sign_citation":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/action/citation_signature","submit_replication":"https://pith.science/pith/NIWJHI77DI2WZO5R3JYCIYIH57/action/replication_record"}},"created_at":"2026-05-17T23:42:35.641527+00:00","updated_at":"2026-05-17T23:42:35.641527+00:00"}