{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2DRTJ4D5UHC5VAX76FNY52BSXF","short_pith_number":"pith:2DRTJ4D5","schema_version":"1.0","canonical_sha256":"d0e334f07da1c5da82fff15b8ee832b97b561e935f39cfae262a03c3615ddf6a","source":{"kind":"arxiv","id":"2310.12371","version":1},"attestation_state":"computed","paper":{"title":"Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ante Jukic, Boris Ginsburg, Coleman Hooper, He Huang, Jagadeesh Balam, Kunal Dhawan, Nithin Koluguri, Tae Jin Park","submitted_at":"2023-10-18T22:46:20Z","abstract_excerpt":"We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap via the adjustment of statistical parameters. This capability offers a tailored training environment for developing neural models suited for speaker diarization and voice activity detection. The acquisition of substantial datasets for speaker diarization often presents a significant challenge, particularly in multi-speaker scenarios. Furthermore, the precise "},"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":"2310.12371","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-10-18T22:46:20Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"efedf5caa1babd1d42799b20c384343d443043b5f3906eee03c8bcca4e16c350","abstract_canon_sha256":"85b1514cc15720c3433e5916aff6656ccc2818df7dff0363cdc1c5d55581e82a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:37.108970Z","signature_b64":"jhs1c9v1m5GOimdFJJH5ooy8slMgqzYtAwEWcpM0Bb39BfhggH13k/nTSKy4mWTHrENuYiTlzLjtY4SfwgqDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0e334f07da1c5da82fff15b8ee832b97b561e935f39cfae262a03c3615ddf6a","last_reissued_at":"2026-07-05T07:02:37.108498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:37.108498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Ante Jukic, Boris Ginsburg, Coleman Hooper, He Huang, Jagadeesh Balam, Kunal Dhawan, Nithin Koluguri, Tae Jin Park","submitted_at":"2023-10-18T22:46:20Z","abstract_excerpt":"We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap via the adjustment of statistical parameters. This capability offers a tailored training environment for developing neural models suited for speaker diarization and voice activity detection. The acquisition of substantial datasets for speaker diarization often presents a significant challenge, particularly in multi-speaker scenarios. Furthermore, the precise "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12371","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.12371/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":"2310.12371","created_at":"2026-07-05T07:02:37.108568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12371v1","created_at":"2026-07-05T07:02:37.108568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12371","created_at":"2026-07-05T07:02:37.108568+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DRTJ4D5UHC5","created_at":"2026-07-05T07:02:37.108568+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DRTJ4D5UHC5VAX7","created_at":"2026-07-05T07:02:37.108568+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DRTJ4D5","created_at":"2026-07-05T07:02:37.108568+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/2DRTJ4D5UHC5VAX76FNY52BSXF","json":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF.json","graph_json":"https://pith.science/api/pith-number/2DRTJ4D5UHC5VAX76FNY52BSXF/graph.json","events_json":"https://pith.science/api/pith-number/2DRTJ4D5UHC5VAX76FNY52BSXF/events.json","paper":"https://pith.science/paper/2DRTJ4D5"},"agent_actions":{"view_html":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF","download_json":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF.json","view_paper":"https://pith.science/paper/2DRTJ4D5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12371&json=true","fetch_graph":"https://pith.science/api/pith-number/2DRTJ4D5UHC5VAX76FNY52BSXF/graph.json","fetch_events":"https://pith.science/api/pith-number/2DRTJ4D5UHC5VAX76FNY52BSXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF/action/storage_attestation","attest_author":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF/action/author_attestation","sign_citation":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF/action/citation_signature","submit_replication":"https://pith.science/pith/2DRTJ4D5UHC5VAX76FNY52BSXF/action/replication_record"}},"created_at":"2026-07-05T07:02:37.108568+00:00","updated_at":"2026-07-05T07:02:37.108568+00:00"}