{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OGNB7BNDKJ5PBYE5K37SMNOHA5","short_pith_number":"pith:OGNB7BND","schema_version":"1.0","canonical_sha256":"719a1f85a3527af0e09d56ff2635c70779906163359f0ab4ec986c85d30fa05f","source":{"kind":"arxiv","id":"2410.22350","version":1},"attestation_state":"computed","paper":{"title":"Quality-Aware End-to-End Audio-Visual Neural Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chin-Hui Lee, Jun Du, Mao-Kui He, Qing-Feng Liu, Shu-Tong Niu","submitted_at":"2024-10-15T05:48:30Z","abstract_excerpt":"In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series of binary classification output layers to simultaneously identify the activities of all speakers. This end-to-end framework is meticulously designed to effectively handle situations of overlapping speech, providing accurate discrimination between speech and non-speech segments through the utilization of multi-modal information. Next, we employ a quality-aware"},"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":"2410.22350","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-10-15T05:48:30Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a3e65e3ee685f938e3e1d36e0cf37fefdc9ec328f98c3b242573d83fddbb3482","abstract_canon_sha256":"651f95bd6378018a6519b26b1acf4c91ec38101363872ed16bd9638f13134252"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:15.203100Z","signature_b64":"LV9dy8+X0eVAe6WA+MLS8Wo7Yl6GiLoYLt5i+gz2NR0U/ziDSkk6G8lJF+iNhrcxGRLYE/6bqh+3bsgbZkqdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"719a1f85a3527af0e09d56ff2635c70779906163359f0ab4ec986c85d30fa05f","last_reissued_at":"2026-07-05T09:28:15.202689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:15.202689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quality-Aware End-to-End Audio-Visual Neural Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Chin-Hui Lee, Jun Du, Mao-Kui He, Qing-Feng Liu, Shu-Tong Niu","submitted_at":"2024-10-15T05:48:30Z","abstract_excerpt":"In this paper, we propose a quality-aware end-to-end audio-visual neural speaker diarization framework, which comprises three key techniques. First, our audio-visual model takes both audio and visual features as inputs, utilizing a series of binary classification output layers to simultaneously identify the activities of all speakers. This end-to-end framework is meticulously designed to effectively handle situations of overlapping speech, providing accurate discrimination between speech and non-speech segments through the utilization of multi-modal information. Next, we employ a quality-aware"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22350","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/2410.22350/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":"2410.22350","created_at":"2026-07-05T09:28:15.202744+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.22350v1","created_at":"2026-07-05T09:28:15.202744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22350","created_at":"2026-07-05T09:28:15.202744+00:00"},{"alias_kind":"pith_short_12","alias_value":"OGNB7BNDKJ5P","created_at":"2026-07-05T09:28:15.202744+00:00"},{"alias_kind":"pith_short_16","alias_value":"OGNB7BNDKJ5PBYE5","created_at":"2026-07-05T09:28:15.202744+00:00"},{"alias_kind":"pith_short_8","alias_value":"OGNB7BND","created_at":"2026-07-05T09:28:15.202744+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/OGNB7BNDKJ5PBYE5K37SMNOHA5","json":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5.json","graph_json":"https://pith.science/api/pith-number/OGNB7BNDKJ5PBYE5K37SMNOHA5/graph.json","events_json":"https://pith.science/api/pith-number/OGNB7BNDKJ5PBYE5K37SMNOHA5/events.json","paper":"https://pith.science/paper/OGNB7BND"},"agent_actions":{"view_html":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5","download_json":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5.json","view_paper":"https://pith.science/paper/OGNB7BND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.22350&json=true","fetch_graph":"https://pith.science/api/pith-number/OGNB7BNDKJ5PBYE5K37SMNOHA5/graph.json","fetch_events":"https://pith.science/api/pith-number/OGNB7BNDKJ5PBYE5K37SMNOHA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5/action/storage_attestation","attest_author":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5/action/author_attestation","sign_citation":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5/action/citation_signature","submit_replication":"https://pith.science/pith/OGNB7BNDKJ5PBYE5K37SMNOHA5/action/replication_record"}},"created_at":"2026-07-05T09:28:15.202744+00:00","updated_at":"2026-07-05T09:28:15.202744+00:00"}