{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6QIUNOVLUTYLNBZNBE7N552RB3","short_pith_number":"pith:6QIUNOVL","schema_version":"1.0","canonical_sha256":"f41146baaba4f0b6872d093edef7510ee1e76dc3d511c28370b5e0bec67b70af","source":{"kind":"arxiv","id":"2309.09180","version":2},"attestation_state":"computed","paper":{"title":"Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chin-Hui Lee, Gaobin Yang, Jun Du, Maokui He, Ruoyu Wang, Shilong Wu, Shuangqing Qian, Shutong Niu, Yanyan Yue","submitted_at":"2023-09-17T07:08:06Z","abstract_excerpt":"We propose a novel neural speaker diarization system using memory-aware multi-speaker embedding with sequence-to-sequence architecture (NSD-MS2S), which integrates the strengths of memory-aware multi-speaker embedding (MA-MSE) and sequence-to-sequence (Seq2Seq) architecture, leading to improvement in both efficiency and performance. Next, we further decrease the memory occupation of decoding by incorporating input features fusion and then employ a multi-head attention mechanism to capture features at different levels. NSD-MS2S achieved a macro diarization error rate (DER) of 15.9% on the CHiME"},"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":"2309.09180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-17T07:08:06Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"a3e53ff2e6ea243ad28e5b0a65ada6d5dc60e97d42aff2fd641803f81a163628","abstract_canon_sha256":"bccacb8b2d14c26b95a13763914f363938abd71e9abf084b3333abbd92f31323"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:50.719444Z","signature_b64":"Lt6tgvs4Ds2OhdjwJGiazRqQCZhgsN7usZyrkjGE2084OGjw/GMXBoaF5Gy1IrMeCDeKE0V+4YaBbZiDWPiKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f41146baaba4f0b6872d093edef7510ee1e76dc3d511c28370b5e0bec67b70af","last_reissued_at":"2026-07-05T07:27:50.718895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:50.718895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chin-Hui Lee, Gaobin Yang, Jun Du, Maokui He, Ruoyu Wang, Shilong Wu, Shuangqing Qian, Shutong Niu, Yanyan Yue","submitted_at":"2023-09-17T07:08:06Z","abstract_excerpt":"We propose a novel neural speaker diarization system using memory-aware multi-speaker embedding with sequence-to-sequence architecture (NSD-MS2S), which integrates the strengths of memory-aware multi-speaker embedding (MA-MSE) and sequence-to-sequence (Seq2Seq) architecture, leading to improvement in both efficiency and performance. Next, we further decrease the memory occupation of decoding by incorporating input features fusion and then employ a multi-head attention mechanism to capture features at different levels. NSD-MS2S achieved a macro diarization error rate (DER) of 15.9% on the CHiME"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09180","kind":"arxiv","version":2},"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/2309.09180/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":"2309.09180","created_at":"2026-07-05T07:27:50.718956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09180v2","created_at":"2026-07-05T07:27:50.718956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09180","created_at":"2026-07-05T07:27:50.718956+00:00"},{"alias_kind":"pith_short_12","alias_value":"6QIUNOVLUTYL","created_at":"2026-07-05T07:27:50.718956+00:00"},{"alias_kind":"pith_short_16","alias_value":"6QIUNOVLUTYLNBZN","created_at":"2026-07-05T07:27:50.718956+00:00"},{"alias_kind":"pith_short_8","alias_value":"6QIUNOVL","created_at":"2026-07-05T07:27:50.718956+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/6QIUNOVLUTYLNBZNBE7N552RB3","json":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3.json","graph_json":"https://pith.science/api/pith-number/6QIUNOVLUTYLNBZNBE7N552RB3/graph.json","events_json":"https://pith.science/api/pith-number/6QIUNOVLUTYLNBZNBE7N552RB3/events.json","paper":"https://pith.science/paper/6QIUNOVL"},"agent_actions":{"view_html":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3","download_json":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3.json","view_paper":"https://pith.science/paper/6QIUNOVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09180&json=true","fetch_graph":"https://pith.science/api/pith-number/6QIUNOVLUTYLNBZNBE7N552RB3/graph.json","fetch_events":"https://pith.science/api/pith-number/6QIUNOVLUTYLNBZNBE7N552RB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3/action/storage_attestation","attest_author":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3/action/author_attestation","sign_citation":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3/action/citation_signature","submit_replication":"https://pith.science/pith/6QIUNOVLUTYLNBZNBE7N552RB3/action/replication_record"}},"created_at":"2026-07-05T07:27:50.718956+00:00","updated_at":"2026-07-05T07:27:50.718956+00:00"}