{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I5XC2WOUBUQE6AICVPPKYRNOCA","short_pith_number":"pith:I5XC2WOU","schema_version":"1.0","canonical_sha256":"476e2d59d40d204f0102abdeac45ae1027a05b76321db53c2f83560548256828","source":{"kind":"arxiv","id":"2109.02002","version":2},"attestation_state":"computed","paper":{"title":"The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Danwei Cai, Jin Wang, Junjie Wang, Lin Yang, Ming Li, Qingjian Lin, Weiqing Wang","submitted_at":"2021-09-05T05:45:52Z","abstract_excerpt":"This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4. Our system including a voice activity detection (VAD) model, a speaker embedding model, two clustering-based speaker diarization systems with different similarity measurements, two different overlapped speech detection (OSD) models, and a target-speaker voice activity detection (TS-VAD) model. Our final submission, consisting of 5 independent systems, achieves a DER of 5.07% on the challenge test set."},"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":"2109.02002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2021-09-05T05:45:52Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"9b04397d37e780bc889a1fb1b99b2fac037cfae2d348fce101e262d95b56095c","abstract_canon_sha256":"e496408ffc0ab7e5a4e35046866c69c79b9079e98e494705b98f72982f5b89bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:17.288565Z","signature_b64":"8ljcpYtgYa/UYJUyOwrrmaDpV0jqdCWVsx3BVYDVewS7Se5a8YsNWe2zLKsv0Cf6V9I/qxsipmBbcgsihCOTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"476e2d59d40d204f0102abdeac45ae1027a05b76321db53c2f83560548256828","last_reissued_at":"2026-07-05T03:12:17.288184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:17.288184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Danwei Cai, Jin Wang, Junjie Wang, Lin Yang, Ming Li, Qingjian Lin, Weiqing Wang","submitted_at":"2021-09-05T05:45:52Z","abstract_excerpt":"This report describes the submission of the DKU-DukeECE-Lenovo team to the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2021 track 4. Our system including a voice activity detection (VAD) model, a speaker embedding model, two clustering-based speaker diarization systems with different similarity measurements, two different overlapped speech detection (OSD) models, and a target-speaker voice activity detection (TS-VAD) model. Our final submission, consisting of 5 independent systems, achieves a DER of 5.07% on the challenge test set."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02002","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/2109.02002/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":"2109.02002","created_at":"2026-07-05T03:12:17.288245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02002v2","created_at":"2026-07-05T03:12:17.288245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02002","created_at":"2026-07-05T03:12:17.288245+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5XC2WOUBUQE","created_at":"2026-07-05T03:12:17.288245+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5XC2WOUBUQE6AIC","created_at":"2026-07-05T03:12:17.288245+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5XC2WOU","created_at":"2026-07-05T03:12:17.288245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22467","citing_title":"DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA","json":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA.json","graph_json":"https://pith.science/api/pith-number/I5XC2WOUBUQE6AICVPPKYRNOCA/graph.json","events_json":"https://pith.science/api/pith-number/I5XC2WOUBUQE6AICVPPKYRNOCA/events.json","paper":"https://pith.science/paper/I5XC2WOU"},"agent_actions":{"view_html":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA","download_json":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA.json","view_paper":"https://pith.science/paper/I5XC2WOU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02002&json=true","fetch_graph":"https://pith.science/api/pith-number/I5XC2WOUBUQE6AICVPPKYRNOCA/graph.json","fetch_events":"https://pith.science/api/pith-number/I5XC2WOUBUQE6AICVPPKYRNOCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA/action/storage_attestation","attest_author":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA/action/author_attestation","sign_citation":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA/action/citation_signature","submit_replication":"https://pith.science/pith/I5XC2WOUBUQE6AICVPPKYRNOCA/action/replication_record"}},"created_at":"2026-07-05T03:12:17.288245+00:00","updated_at":"2026-07-05T03:12:17.288245+00:00"}