{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4H3TCR2H4XYE7FVT24QB4GL2GC","short_pith_number":"pith:4H3TCR2H","schema_version":"1.0","canonical_sha256":"e1f7314747e5f04f96b3d7201e197a30b2ad06a93e677a5f55f7c4645759b442","source":{"kind":"arxiv","id":"2006.01796","version":1},"attestation_state":"computed","paper":{"title":"Neural Speaker Diarization with Speaker-Wise Chain Rule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jing Shi, Kenji Nagamatsu, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Yusuke Fujita","submitted_at":"2020-06-02T17:28:12Z","abstract_excerpt":"Speaker diarization is an essential step for processing multi-speaker audio. Although an end-to-end neural diarization (EEND) method achieved state-of-the-art performance, it is limited to a fixed number of speakers. In this paper, we solve this fixed number of speaker issue by a novel speaker-wise conditional inference method based on the probabilistic chain rule. In the proposed method, each speaker's speech activity is regarded as a single random variable, and is estimated sequentially conditioned on previously estimated other speakers' speech activities. Similar to other sequence-to-sequen"},"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":"2006.01796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-02T17:28:12Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"9d378e73225d7217019fd00a1f57ede77b2a900e2764c7cdf9fbc3204f0babb6","abstract_canon_sha256":"b02714633106ecf761a81be83418f652b88064f16a727647e3d40eb212485e6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:34.255509Z","signature_b64":"ZuQwiSW1y57LMpiuYXwBxdyo3UTJw5lg6ZcCb0lnoXqTkkFCxVOuQnb1eZgj7fxgpkh0q2DA0nrLaZk+j1i9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1f7314747e5f04f96b3d7201e197a30b2ad06a93e677a5f55f7c4645759b442","last_reissued_at":"2026-07-05T01:07:34.255016Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:34.255016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Speaker Diarization with Speaker-Wise Chain Rule","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jing Shi, Kenji Nagamatsu, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Yusuke Fujita","submitted_at":"2020-06-02T17:28:12Z","abstract_excerpt":"Speaker diarization is an essential step for processing multi-speaker audio. Although an end-to-end neural diarization (EEND) method achieved state-of-the-art performance, it is limited to a fixed number of speakers. In this paper, we solve this fixed number of speaker issue by a novel speaker-wise conditional inference method based on the probabilistic chain rule. In the proposed method, each speaker's speech activity is regarded as a single random variable, and is estimated sequentially conditioned on previously estimated other speakers' speech activities. Similar to other sequence-to-sequen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.01796","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/2006.01796/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":"2006.01796","created_at":"2026-07-05T01:07:34.255071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.01796v1","created_at":"2026-07-05T01:07:34.255071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.01796","created_at":"2026-07-05T01:07:34.255071+00:00"},{"alias_kind":"pith_short_12","alias_value":"4H3TCR2H4XYE","created_at":"2026-07-05T01:07:34.255071+00:00"},{"alias_kind":"pith_short_16","alias_value":"4H3TCR2H4XYE7FVT","created_at":"2026-07-05T01:07:34.255071+00:00"},{"alias_kind":"pith_short_8","alias_value":"4H3TCR2H","created_at":"2026-07-05T01:07:34.255071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18446","citing_title":"Streaming Sortformer: Speaker Cache-Based Online Speaker Diarization with Arrival-Time Ordering","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC","json":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC.json","graph_json":"https://pith.science/api/pith-number/4H3TCR2H4XYE7FVT24QB4GL2GC/graph.json","events_json":"https://pith.science/api/pith-number/4H3TCR2H4XYE7FVT24QB4GL2GC/events.json","paper":"https://pith.science/paper/4H3TCR2H"},"agent_actions":{"view_html":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC","download_json":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC.json","view_paper":"https://pith.science/paper/4H3TCR2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.01796&json=true","fetch_graph":"https://pith.science/api/pith-number/4H3TCR2H4XYE7FVT24QB4GL2GC/graph.json","fetch_events":"https://pith.science/api/pith-number/4H3TCR2H4XYE7FVT24QB4GL2GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC/action/storage_attestation","attest_author":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC/action/author_attestation","sign_citation":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC/action/citation_signature","submit_replication":"https://pith.science/pith/4H3TCR2H4XYE7FVT24QB4GL2GC/action/replication_record"}},"created_at":"2026-07-05T01:07:34.255071+00:00","updated_at":"2026-07-05T01:07:34.255071+00:00"}