{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VR53NKX4E7WJBJHEQ2MDXZZEKY","short_pith_number":"pith:VR53NKX4","schema_version":"1.0","canonical_sha256":"ac7bb6aafc27ec90a4e486983be724561b0856f207d022070b2a2591b37c892c","source":{"kind":"arxiv","id":"2305.10704","version":3},"attestation_state":"computed","paper":{"title":"Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Zhengyang Chen","submitted_at":"2023-05-18T04:35:02Z","abstract_excerpt":"This paper proposes a novel Attention-based Encoder-Decoder network for End-to-End Neural speaker Diarization (AED-EEND). In AED-EEND system, we incorporate the target speaker enrollment information used in target speaker voice activity detection (TS-VAD) to calculate the attractor, which can mitigate the speaker permutation problem and facilitate easier model convergence. In the training process, we propose a teacher-forcing strategy to obtain the enrollment information using the ground-truth label. Furthermore, we propose three heuristic decoding methods to identify the enrollment area for e"},"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":"2305.10704","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-18T04:35:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d86e25d22504752fa60df0a100e37e36a911586b4c5312694f5d936827c6f916","abstract_canon_sha256":"d6484cc88695d5a4d68d8428d12817797c3bc2de9875e039d1c1848c9363897d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:18.198251Z","signature_b64":"Ihd/GrCrkUYZqFhs/S5ZNWmYjant0KlCPatY5Pwsylocd4p+JbtICO/K/Wa46ePbKH2BCPGPROIjSTdVhsttAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac7bb6aafc27ec90a4e486983be724561b0856f207d022070b2a2591b37c892c","last_reissued_at":"2026-07-05T06:41:18.197762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:18.197762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-based Encoder-Decoder Network for End-to-End Neural Speaker Diarization with Target Speaker Attractor","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Zhengyang Chen","submitted_at":"2023-05-18T04:35:02Z","abstract_excerpt":"This paper proposes a novel Attention-based Encoder-Decoder network for End-to-End Neural speaker Diarization (AED-EEND). In AED-EEND system, we incorporate the target speaker enrollment information used in target speaker voice activity detection (TS-VAD) to calculate the attractor, which can mitigate the speaker permutation problem and facilitate easier model convergence. In the training process, we propose a teacher-forcing strategy to obtain the enrollment information using the ground-truth label. Furthermore, we propose three heuristic decoding methods to identify the enrollment area for e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10704","kind":"arxiv","version":3},"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/2305.10704/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":"2305.10704","created_at":"2026-07-05T06:41:18.197835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10704v3","created_at":"2026-07-05T06:41:18.197835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10704","created_at":"2026-07-05T06:41:18.197835+00:00"},{"alias_kind":"pith_short_12","alias_value":"VR53NKX4E7WJ","created_at":"2026-07-05T06:41:18.197835+00:00"},{"alias_kind":"pith_short_16","alias_value":"VR53NKX4E7WJBJHE","created_at":"2026-07-05T06:41:18.197835+00:00"},{"alias_kind":"pith_short_8","alias_value":"VR53NKX4","created_at":"2026-07-05T06:41:18.197835+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/VR53NKX4E7WJBJHEQ2MDXZZEKY","json":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY.json","graph_json":"https://pith.science/api/pith-number/VR53NKX4E7WJBJHEQ2MDXZZEKY/graph.json","events_json":"https://pith.science/api/pith-number/VR53NKX4E7WJBJHEQ2MDXZZEKY/events.json","paper":"https://pith.science/paper/VR53NKX4"},"agent_actions":{"view_html":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY","download_json":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY.json","view_paper":"https://pith.science/paper/VR53NKX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10704&json=true","fetch_graph":"https://pith.science/api/pith-number/VR53NKX4E7WJBJHEQ2MDXZZEKY/graph.json","fetch_events":"https://pith.science/api/pith-number/VR53NKX4E7WJBJHEQ2MDXZZEKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY/action/storage_attestation","attest_author":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY/action/author_attestation","sign_citation":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY/action/citation_signature","submit_replication":"https://pith.science/pith/VR53NKX4E7WJBJHEQ2MDXZZEKY/action/replication_record"}},"created_at":"2026-07-05T06:41:18.197835+00:00","updated_at":"2026-07-05T06:41:18.197835+00:00"}