{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WF7ODPVMP65VNCE6VZ6GQQP6QD","short_pith_number":"pith:WF7ODPVM","schema_version":"1.0","canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","source":{"kind":"arxiv","id":"2211.01299","version":2},"attestation_state":"computed","paper":{"title":"Late Audio-Visual Fusion for In-The-Wild Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Subramanian, Fran\\c{c}ois G. Germain, Gordon Wichern, Jonathan Le Roux, Zexu Pan","submitted_at":"2022-11-02T17:20:42Z","abstract_excerpt":"Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on-screen speakers. We address this gap by proposing an audio-visual diarization model which combines audio-only and visual-centric sub-systems via late fusion. For audio, we show that an attractor-based end-to-end system (EEND-EDA) performs remarkably well when trained with our proposed recipe of a simulated proxy dataset, and propose an improved version, EEND-EDA++, that uses attention in decoding and a speaker recog"},"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":"2211.01299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T17:20:42Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"7bc40cdec83ea3e798481ef8647ba954662f86af24610d83dcb0a16b176e7741","abstract_canon_sha256":"5347009ab430e4d3fb057c2ef68a47d7ba4927fe2697d1e91026078c8137bc83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:53.477399Z","signature_b64":"r6AFc0IvQaH3kRutW8nnTutIEejsW4tbHEFCl7NMZcE8akwvcVcTkUb1kYehAsfacb0pwjDEbZu0ynER62mPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17ee1beac7fbb56889eae7c6841fe80c6574837b74a219783f40828d4366e28","last_reissued_at":"2026-07-05T06:54:53.476896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:53.476896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Late Audio-Visual Fusion for In-The-Wild Speaker Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aswin Subramanian, Fran\\c{c}ois G. Germain, Gordon Wichern, Jonathan Le Roux, Zexu Pan","submitted_at":"2022-11-02T17:20:42Z","abstract_excerpt":"Speaker diarization is well studied for constrained audios but little explored for challenging in-the-wild videos, which have more speakers, shorter utterances, and inconsistent on-screen speakers. We address this gap by proposing an audio-visual diarization model which combines audio-only and visual-centric sub-systems via late fusion. For audio, we show that an attractor-based end-to-end system (EEND-EDA) performs remarkably well when trained with our proposed recipe of a simulated proxy dataset, and propose an improved version, EEND-EDA++, that uses attention in decoding and a speaker recog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01299","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/2211.01299/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":"2211.01299","created_at":"2026-07-05T06:54:53.476960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01299v2","created_at":"2026-07-05T06:54:53.476960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01299","created_at":"2026-07-05T06:54:53.476960+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF7ODPVMP65V","created_at":"2026-07-05T06:54:53.476960+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF7ODPVMP65VNCE6","created_at":"2026-07-05T06:54:53.476960+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF7ODPVM","created_at":"2026-07-05T06:54:53.476960+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/WF7ODPVMP65VNCE6VZ6GQQP6QD","json":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD.json","graph_json":"https://pith.science/api/pith-number/WF7ODPVMP65VNCE6VZ6GQQP6QD/graph.json","events_json":"https://pith.science/api/pith-number/WF7ODPVMP65VNCE6VZ6GQQP6QD/events.json","paper":"https://pith.science/paper/WF7ODPVM"},"agent_actions":{"view_html":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD","download_json":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD.json","view_paper":"https://pith.science/paper/WF7ODPVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01299&json=true","fetch_graph":"https://pith.science/api/pith-number/WF7ODPVMP65VNCE6VZ6GQQP6QD/graph.json","fetch_events":"https://pith.science/api/pith-number/WF7ODPVMP65VNCE6VZ6GQQP6QD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/action/storage_attestation","attest_author":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/action/author_attestation","sign_citation":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/action/citation_signature","submit_replication":"https://pith.science/pith/WF7ODPVMP65VNCE6VZ6GQQP6QD/action/replication_record"}},"created_at":"2026-07-05T06:54:53.476960+00:00","updated_at":"2026-07-05T06:54:53.476960+00:00"}