{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:33FIRXIDNRSQ32SFKU75RZ2V4N","short_pith_number":"pith:33FIRXID","schema_version":"1.0","canonical_sha256":"deca88dd036c650dea45553fd8e755e36b8d7c643024776dfa304884da81ed07","source":{"kind":"arxiv","id":"2308.07595","version":2},"attestation_state":"computed","paper":{"title":"The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Guoqing Zhao, Ming Cheng, Ming Li, Ning Jiang, Weiqing Wang, Xiaoyi Qin, Yuke Lin","submitted_at":"2023-08-15T06:50:07Z","abstract_excerpt":"This paper describes the DKU-MSXF submission to track 4 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our system pipeline contains voice activity detection, clustering-based diarization, overlapped speech detection, and target-speaker voice activity detection, where each procedure has a fused output from 3 sub-models. Finally, we fuse different clustering-based and TSVAD-based diarization systems using DOVER-Lap and achieve the 4.30% diarization error rate (DER), which ranks first place on track 4 of the challenge leaderboard."},"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":"2308.07595","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-08-15T06:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"6e2acd57ab20d7dc84e68a740be0da05462f37aea17a7bf9e4c59d2c3c0e802a","abstract_canon_sha256":"e447a581fc02f373917d82de56be3fa8824b123fac5b21e9afc55056099fdd28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:07.551817Z","signature_b64":"diggYYFSDdBVCdR21KICls5waxBOysZ/E0MArMN0querFX1zOuZ9DGEDPWVYvNlV4oHWXahRyLnS3i0qu2sIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deca88dd036c650dea45553fd8e755e36b8d7c643024776dfa304884da81ed07","last_reissued_at":"2026-07-05T06:42:07.551405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:07.551405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The DKU-MSXF Diarization System for the VoxCeleb Speaker Recognition Challenge 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Guoqing Zhao, Ming Cheng, Ming Li, Ning Jiang, Weiqing Wang, Xiaoyi Qin, Yuke Lin","submitted_at":"2023-08-15T06:50:07Z","abstract_excerpt":"This paper describes the DKU-MSXF submission to track 4 of the VoxCeleb Speaker Recognition Challenge 2023 (VoxSRC-23). Our system pipeline contains voice activity detection, clustering-based diarization, overlapped speech detection, and target-speaker voice activity detection, where each procedure has a fused output from 3 sub-models. Finally, we fuse different clustering-based and TSVAD-based diarization systems using DOVER-Lap and achieve the 4.30% diarization error rate (DER), which ranks first place on track 4 of the challenge leaderboard."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07595","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/2308.07595/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":"2308.07595","created_at":"2026-07-05T06:42:07.551464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.07595v2","created_at":"2026-07-05T06:42:07.551464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07595","created_at":"2026-07-05T06:42:07.551464+00:00"},{"alias_kind":"pith_short_12","alias_value":"33FIRXIDNRSQ","created_at":"2026-07-05T06:42:07.551464+00:00"},{"alias_kind":"pith_short_16","alias_value":"33FIRXIDNRSQ32SF","created_at":"2026-07-05T06:42:07.551464+00:00"},{"alias_kind":"pith_short_8","alias_value":"33FIRXID","created_at":"2026-07-05T06:42:07.551464+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/33FIRXIDNRSQ32SFKU75RZ2V4N","json":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N.json","graph_json":"https://pith.science/api/pith-number/33FIRXIDNRSQ32SFKU75RZ2V4N/graph.json","events_json":"https://pith.science/api/pith-number/33FIRXIDNRSQ32SFKU75RZ2V4N/events.json","paper":"https://pith.science/paper/33FIRXID"},"agent_actions":{"view_html":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N","download_json":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N.json","view_paper":"https://pith.science/paper/33FIRXID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.07595&json=true","fetch_graph":"https://pith.science/api/pith-number/33FIRXIDNRSQ32SFKU75RZ2V4N/graph.json","fetch_events":"https://pith.science/api/pith-number/33FIRXIDNRSQ32SFKU75RZ2V4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N/action/storage_attestation","attest_author":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N/action/author_attestation","sign_citation":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N/action/citation_signature","submit_replication":"https://pith.science/pith/33FIRXIDNRSQ32SFKU75RZ2V4N/action/replication_record"}},"created_at":"2026-07-05T06:42:07.551464+00:00","updated_at":"2026-07-05T06:42:07.551464+00:00"}