{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:676ZRSTAPL5NDSG54QCDFF35OY","short_pith_number":"pith:676ZRSTA","schema_version":"1.0","canonical_sha256":"f7fd98ca607afad1c8dde40432977d7603f4f08a873cd72cec4e2706dcdc3f0f","source":{"kind":"arxiv","id":"1906.07955","version":2},"attestation_state":"computed","paper":{"title":"Large-Scale Speaker Diarization of Radio Broadcast Archives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adem Derinel, David A. van Leeuwen, Emre Y{\\i}lmaz, Haizhou Li, Henk van den Heuvel, Niko Brummer, Zhou Kun","submitted_at":"2019-06-19T07:58:42Z","abstract_excerpt":"This paper describes our initial efforts to build a large-scale speaker diarization (SD) and identification system on a recently digitized radio broadcast archive from the Netherlands which has more than 6500 audio tapes with 3000 hours of Frisian-Dutch speech recorded between 1950-2016. The employed large-scale diarization scheme involves two stages: (1) tape-level speaker diarization providing pseudo-speaker identities and (2) speaker linking to relate pseudo-speakers appearing in multiple tapes. Having access to the speaker models of several frequently appearing speakers from the previously"},"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":"1906.07955","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-19T07:58:42Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"de0891588da85bc02897aca3c55e4ef329b9d09b6c68b76e74ea0e7304536468","abstract_canon_sha256":"9b55996b866e5bba6046e0d1583baa59976fe513528ed6dc003171062ec75cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:02.017625Z","signature_b64":"GPL03fdPWk/pCBUelr/dSf5+OdU3JTDAlq9t3buLYayjJ0K1nkcLW7CwDvQByFph6g6SwjX6B2l1GRbEwOlFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7fd98ca607afad1c8dde40432977d7603f4f08a873cd72cec4e2706dcdc3f0f","last_reissued_at":"2026-05-17T23:42:02.016998Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:02.016998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Speaker Diarization of Radio Broadcast Archives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adem Derinel, David A. van Leeuwen, Emre Y{\\i}lmaz, Haizhou Li, Henk van den Heuvel, Niko Brummer, Zhou Kun","submitted_at":"2019-06-19T07:58:42Z","abstract_excerpt":"This paper describes our initial efforts to build a large-scale speaker diarization (SD) and identification system on a recently digitized radio broadcast archive from the Netherlands which has more than 6500 audio tapes with 3000 hours of Frisian-Dutch speech recorded between 1950-2016. The employed large-scale diarization scheme involves two stages: (1) tape-level speaker diarization providing pseudo-speaker identities and (2) speaker linking to relate pseudo-speakers appearing in multiple tapes. Having access to the speaker models of several frequently appearing speakers from the previously"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07955","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":""},"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":"1906.07955","created_at":"2026-05-17T23:42:02.017074+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07955v2","created_at":"2026-05-17T23:42:02.017074+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07955","created_at":"2026-05-17T23:42:02.017074+00:00"},{"alias_kind":"pith_short_12","alias_value":"676ZRSTAPL5N","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"676ZRSTAPL5NDSG5","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"676ZRSTA","created_at":"2026-05-18T12:33:10.108867+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/676ZRSTAPL5NDSG54QCDFF35OY","json":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY.json","graph_json":"https://pith.science/api/pith-number/676ZRSTAPL5NDSG54QCDFF35OY/graph.json","events_json":"https://pith.science/api/pith-number/676ZRSTAPL5NDSG54QCDFF35OY/events.json","paper":"https://pith.science/paper/676ZRSTA"},"agent_actions":{"view_html":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY","download_json":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY.json","view_paper":"https://pith.science/paper/676ZRSTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07955&json=true","fetch_graph":"https://pith.science/api/pith-number/676ZRSTAPL5NDSG54QCDFF35OY/graph.json","fetch_events":"https://pith.science/api/pith-number/676ZRSTAPL5NDSG54QCDFF35OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY/action/storage_attestation","attest_author":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY/action/author_attestation","sign_citation":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY/action/citation_signature","submit_replication":"https://pith.science/pith/676ZRSTAPL5NDSG54QCDFF35OY/action/replication_record"}},"created_at":"2026-05-17T23:42:02.017074+00:00","updated_at":"2026-05-17T23:42:02.017074+00:00"}