{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NCJ2WPGPN62GDY5EU5ZZLLPBZL","short_pith_number":"pith:NCJ2WPGP","schema_version":"1.0","canonical_sha256":"6893ab3ccf6fb461e3a4a77395ade1cad533ce5b1dae37ceb4ca199494af9b7e","source":{"kind":"arxiv","id":"1810.04719","version":7},"attestation_state":"computed","paper":{"title":"Fully Supervised Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.AS","authors_text":"Aonan Zhang, Chong Wang, John Paisley, Quan Wang, Zhenyao Zhu","submitted_at":"2018-10-10T19:21:44Z","abstract_excerpt":"In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input utterances, each individual speaker is modeled by a parameter-sharing RNN, while the RNN states for different speakers interleave in the time domain. This RNN is naturally integrated with a distance-dependent Chinese restaurant process (ddCRP) to accommodate an unknown number of speakers. Our system is fully supervised and is able to learn from examples where time-stamped"},"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":"1810.04719","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-10-10T19:21:44Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"59c8256baf4b08eedfd799051c99d414ba0db81710bcdc50b513f6594c91422a","abstract_canon_sha256":"309d09b03b0d37a6a6ff99b867f4515fc5fb1432a5d0e67da2b3b1a82a801848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:41.850505Z","signature_b64":"ymuCbEQnpjpV8PGX4IVrE9y+iuK4nlG6Yso4Vfsqbj3ffmELbgx3kzen+3fbadv15+WXkbH2RvD8t+wmaj+SBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6893ab3ccf6fb461e3a4a77395ade1cad533ce5b1dae37ceb4ca199494af9b7e","last_reissued_at":"2026-05-17T23:53:41.849929Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:41.849929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Supervised Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"eess.AS","authors_text":"Aonan Zhang, Chong Wang, John Paisley, Quan Wang, Zhenyao Zhu","submitted_at":"2018-10-10T19:21:44Z","abstract_excerpt":"In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN). Given extracted speaker-discriminative embeddings (a.k.a. d-vectors) from input utterances, each individual speaker is modeled by a parameter-sharing RNN, while the RNN states for different speakers interleave in the time domain. This RNN is naturally integrated with a distance-dependent Chinese restaurant process (ddCRP) to accommodate an unknown number of speakers. Our system is fully supervised and is able to learn from examples where time-stamped"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.04719","kind":"arxiv","version":7},"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":"1810.04719","created_at":"2026-05-17T23:53:41.850015+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.04719v7","created_at":"2026-05-17T23:53:41.850015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.04719","created_at":"2026-05-17T23:53:41.850015+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCJ2WPGPN62G","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCJ2WPGPN62GDY5E","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCJ2WPGP","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05337","citing_title":"Joint Speech Recognition and Speaker Diarization via Sequence Transduction","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL","json":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL.json","graph_json":"https://pith.science/api/pith-number/NCJ2WPGPN62GDY5EU5ZZLLPBZL/graph.json","events_json":"https://pith.science/api/pith-number/NCJ2WPGPN62GDY5EU5ZZLLPBZL/events.json","paper":"https://pith.science/paper/NCJ2WPGP"},"agent_actions":{"view_html":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL","download_json":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL.json","view_paper":"https://pith.science/paper/NCJ2WPGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.04719&json=true","fetch_graph":"https://pith.science/api/pith-number/NCJ2WPGPN62GDY5EU5ZZLLPBZL/graph.json","fetch_events":"https://pith.science/api/pith-number/NCJ2WPGPN62GDY5EU5ZZLLPBZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL/action/storage_attestation","attest_author":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL/action/author_attestation","sign_citation":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL/action/citation_signature","submit_replication":"https://pith.science/pith/NCJ2WPGPN62GDY5EU5ZZLLPBZL/action/replication_record"}},"created_at":"2026-05-17T23:53:41.850015+00:00","updated_at":"2026-05-17T23:53:41.850015+00:00"}