{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7X3FEAJOPQFPC55C5TP6QHGUVI","short_pith_number":"pith:7X3FEAJO","schema_version":"1.0","canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","source":{"kind":"arxiv","id":"2309.06672","version":1},"attestation_state":"computed","paper":{"title":"Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Zhengyang Chen","submitted_at":"2023-09-13T02:17:13Z","abstract_excerpt":"Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For "},"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":"2309.06672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-13T02:17:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e6a0ce0080f4411bebd4fb74a25f1d84ca91a18ceb7edd9eb9ec289ebc72d6e5","abstract_canon_sha256":"005d06608acbb98d34d5551ee91660be2b10e839cafd844a0dd86059fd9b9351"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:21.123978Z","signature_b64":"OoF9ffFR+Y8JGI//sJfgO46mcQXJnbHMl+VDrrb0X0FNLNXMiqTiF0+mBMb0aVWbLcOtha1A6UpGsLdroavhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf652012e7c0af177a2ecdfe81cd4aa34f03539c65467dd20ba18ed52993a9c","last_reissued_at":"2026-07-05T06:50:21.123534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:21.123534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-based Encoder-Decoder End-to-End Neural Diarization with Embedding Enhancer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Zhengyang Chen","submitted_at":"2023-09-13T02:17:13Z","abstract_excerpt":"Deep neural network-based systems have significantly improved the performance of speaker diarization tasks. However, end-to-end neural diarization (EEND) systems often struggle to generalize to scenarios with an unseen number of speakers, while target speaker voice activity detection (TS-VAD) systems tend to be overly complex. In this paper, we propose a simple attention-based encoder-decoder network for end-to-end neural diarization (AED-EEND). In our training process, we introduce a teacher-forcing strategy to address the speaker permutation problem, leading to faster model convergence. For "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06672","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/2309.06672/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":"2309.06672","created_at":"2026-07-05T06:50:21.123587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.06672v1","created_at":"2026-07-05T06:50:21.123587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06672","created_at":"2026-07-05T06:50:21.123587+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X3FEAJOPQFP","created_at":"2026-07-05T06:50:21.123587+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X3FEAJOPQFPC55C","created_at":"2026-07-05T06:50:21.123587+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X3FEAJO","created_at":"2026-07-05T06:50:21.123587+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/7X3FEAJOPQFPC55C5TP6QHGUVI","json":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI.json","graph_json":"https://pith.science/api/pith-number/7X3FEAJOPQFPC55C5TP6QHGUVI/graph.json","events_json":"https://pith.science/api/pith-number/7X3FEAJOPQFPC55C5TP6QHGUVI/events.json","paper":"https://pith.science/paper/7X3FEAJO"},"agent_actions":{"view_html":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI","download_json":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI.json","view_paper":"https://pith.science/paper/7X3FEAJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.06672&json=true","fetch_graph":"https://pith.science/api/pith-number/7X3FEAJOPQFPC55C5TP6QHGUVI/graph.json","fetch_events":"https://pith.science/api/pith-number/7X3FEAJOPQFPC55C5TP6QHGUVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/action/storage_attestation","attest_author":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/action/author_attestation","sign_citation":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/action/citation_signature","submit_replication":"https://pith.science/pith/7X3FEAJOPQFPC55C5TP6QHGUVI/action/replication_record"}},"created_at":"2026-07-05T06:50:21.123587+00:00","updated_at":"2026-07-05T06:50:21.123587+00:00"}