{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R256O7LLOCIDR4STWD7PMG43L6","short_pith_number":"pith:R256O7LL","schema_version":"1.0","canonical_sha256":"8ebbe77d6b709038f253b0fef61b9b5fb093138ef661dc13bdced67533437c32","source":{"kind":"arxiv","id":"1909.05952","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Kenji Nagamatsu, Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, Yusuke Fujita","submitted_at":"2019-09-12T21:12:10Z","abstract_excerpt":"In this paper, we propose a novel end-to-end neural-network-based speaker diarization method. Unlike most existing methods, our proposed method does not have separate modules for extraction and clustering of speaker representations. Instead, our model has a single neural network that directly outputs speaker diarization results. To realize such a model, we formulate the speaker diarization problem as a multi-label classification problem, and introduces a permutation-free objective function to directly minimize diarization errors without being suffered from the speaker-label permutation problem"},"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":"1909.05952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-09-12T21:12:10Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"0013a4b32167e221a850f1979171e9bdf747eebc67b45f36e384e6c9da7f8383","abstract_canon_sha256":"d530673518006c41344da7b1c6cc3b8850695f8214b38fd65226bf9592c91bfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:31.063783Z","signature_b64":"Ihez1e3t7YJ2BE1yl/TYjnvYKLRVtlM2Luq9bW6qPI4cM2tt0RvIsoxjHLquwBlHtBYeYzWtxi0Fb4vICt89Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ebbe77d6b709038f253b0fef61b9b5fb093138ef661dc13bdced67533437c32","last_reissued_at":"2026-07-05T00:04:31.063356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:31.063356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Neural Speaker Diarization with Permutation-Free Objectives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Kenji Nagamatsu, Naoyuki Kanda, Shinji Watanabe, Shota Horiguchi, Yusuke Fujita","submitted_at":"2019-09-12T21:12:10Z","abstract_excerpt":"In this paper, we propose a novel end-to-end neural-network-based speaker diarization method. Unlike most existing methods, our proposed method does not have separate modules for extraction and clustering of speaker representations. Instead, our model has a single neural network that directly outputs speaker diarization results. To realize such a model, we formulate the speaker diarization problem as a multi-label classification problem, and introduces a permutation-free objective function to directly minimize diarization errors without being suffered from the speaker-label permutation problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.05952","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/1909.05952/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":"1909.05952","created_at":"2026-07-05T00:04:31.063406+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.05952v1","created_at":"2026-07-05T00:04:31.063406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.05952","created_at":"2026-07-05T00:04:31.063406+00:00"},{"alias_kind":"pith_short_12","alias_value":"R256O7LLOCID","created_at":"2026-07-05T00:04:31.063406+00:00"},{"alias_kind":"pith_short_16","alias_value":"R256O7LLOCIDR4ST","created_at":"2026-07-05T00:04:31.063406+00:00"},{"alias_kind":"pith_short_8","alias_value":"R256O7LL","created_at":"2026-07-05T00:04:31.063406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02683","citing_title":"Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6","json":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6.json","graph_json":"https://pith.science/api/pith-number/R256O7LLOCIDR4STWD7PMG43L6/graph.json","events_json":"https://pith.science/api/pith-number/R256O7LLOCIDR4STWD7PMG43L6/events.json","paper":"https://pith.science/paper/R256O7LL"},"agent_actions":{"view_html":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6","download_json":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6.json","view_paper":"https://pith.science/paper/R256O7LL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.05952&json=true","fetch_graph":"https://pith.science/api/pith-number/R256O7LLOCIDR4STWD7PMG43L6/graph.json","fetch_events":"https://pith.science/api/pith-number/R256O7LLOCIDR4STWD7PMG43L6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6/action/storage_attestation","attest_author":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6/action/author_attestation","sign_citation":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6/action/citation_signature","submit_replication":"https://pith.science/pith/R256O7LLOCIDR4STWD7PMG43L6/action/replication_record"}},"created_at":"2026-07-05T00:04:31.063406+00:00","updated_at":"2026-07-05T00:04:31.063406+00:00"}