{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:O66MKTYUZQTSMBMTQRBRALSMLQ","short_pith_number":"pith:O66MKTYU","schema_version":"1.0","canonical_sha256":"77bcc54f14cc272605938443102e4c5c003be6ae20e5f46153b9caa2f75158e6","source":{"kind":"arxiv","id":"2309.10674","version":3},"attestation_state":"computed","paper":{"title":"USED: Universal Speaker Extraction and Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Junyi Ao, Mehmet Sinan Y{\\i}ld{\\i}r{\\i}m, Meng Ge, Ruijie Tao, Shuai Wang, Yanmin Qian","submitted_at":"2023-09-19T14:56:31Z","abstract_excerpt":"Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker's voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating `who spoke when'. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about `who spoke what and when', which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain,"},"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":"2309.10674","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-19T14:56:31Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"74ebe088c5afa33560f9ba5c55b7e981884d6a6f72eacaf421377987cf7c4122","abstract_canon_sha256":"919e9bdc5ec19ba17a8cecdab9840546a06a0885718e6c12b3d2113bbc3449d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:31.050284Z","signature_b64":"sCezkkB62gSyOsmangt4y3kiZQYJUVy3zRvO2tXwaIJb0TXx++fJSoiHAM7w7P6DYR+Wh/tT6qy4AFXfYbyADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77bcc54f14cc272605938443102e4c5c003be6ae20e5f46153b9caa2f75158e6","last_reissued_at":"2026-07-05T10:01:31.049868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:31.049868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"USED: Universal Speaker Extraction and Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Junyi Ao, Mehmet Sinan Y{\\i}ld{\\i}r{\\i}m, Meng Ge, Ruijie Tao, Shuai Wang, Yanmin Qian","submitted_at":"2023-09-19T14:56:31Z","abstract_excerpt":"Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker's voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating `who spoke when'. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about `who spoke what and when', which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10674","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/2309.10674/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":"2309.10674","created_at":"2026-07-05T10:01:31.049923+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10674v3","created_at":"2026-07-05T10:01:31.049923+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10674","created_at":"2026-07-05T10:01:31.049923+00:00"},{"alias_kind":"pith_short_12","alias_value":"O66MKTYUZQTS","created_at":"2026-07-05T10:01:31.049923+00:00"},{"alias_kind":"pith_short_16","alias_value":"O66MKTYUZQTSMBMT","created_at":"2026-07-05T10:01:31.049923+00:00"},{"alias_kind":"pith_short_8","alias_value":"O66MKTYU","created_at":"2026-07-05T10:01:31.049923+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/O66MKTYUZQTSMBMTQRBRALSMLQ","json":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ.json","graph_json":"https://pith.science/api/pith-number/O66MKTYUZQTSMBMTQRBRALSMLQ/graph.json","events_json":"https://pith.science/api/pith-number/O66MKTYUZQTSMBMTQRBRALSMLQ/events.json","paper":"https://pith.science/paper/O66MKTYU"},"agent_actions":{"view_html":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ","download_json":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ.json","view_paper":"https://pith.science/paper/O66MKTYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10674&json=true","fetch_graph":"https://pith.science/api/pith-number/O66MKTYUZQTSMBMTQRBRALSMLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/O66MKTYUZQTSMBMTQRBRALSMLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ/action/storage_attestation","attest_author":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ/action/author_attestation","sign_citation":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ/action/citation_signature","submit_replication":"https://pith.science/pith/O66MKTYUZQTSMBMTQRBRALSMLQ/action/replication_record"}},"created_at":"2026-07-05T10:01:31.049923+00:00","updated_at":"2026-07-05T10:01:31.049923+00:00"}