{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PFEVFR6ETYI4T2ZT6AY6KK263W","short_pith_number":"pith:PFEVFR6E","schema_version":"1.0","canonical_sha256":"794952c7c49e11c9eb33f031e52b5edd815426aefd2e5a6e2a5d6ed75e6b496e","source":{"kind":"arxiv","id":"2502.06012","version":1},"attestation_state":"computed","paper":{"title":"Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Jason Clarke, Stefan Goetze, Yoshihiko Gotoh","submitted_at":"2025-02-09T20:06:42Z","abstract_excerpt":"Audiovisual active speaker detection (ASD) addresses the task of determining the speech activity of a candidate speaker given acoustic and visual data. Typically, systems model the temporal correspondence of audiovisual cues, such as the synchronisation between speech and lip movement. Recent work has explored extending this paradigm by additionally leveraging speaker embeddings extracted from candidate speaker reference speech. This paper proposes the speaker comparison auxiliary network (SCAN) which uses speaker-specific information from both reference speech and the candidate audio signal t"},"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":"2502.06012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-02-09T20:06:42Z","cross_cats_sorted":[],"title_canon_sha256":"c0fbc0f6c72433f2bea211fe589c1c832b4477cfe6124a4ad7b694eaaffa39bd","abstract_canon_sha256":"82430de3beef36c726106113d06e0a0088c3f39521a4b3fa4db0db5da8d753d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:46.382651Z","signature_b64":"xRVJ97/46k10NIbAnpwhYAEIJc2YcM4cORNI0E84AHejqQz7gRFxjLW4mQJOlWWK+eqJF1ZsBYH3PVZqOSLbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"794952c7c49e11c9eb33f031e52b5edd815426aefd2e5a6e2a5d6ed75e6b496e","last_reissued_at":"2026-07-05T10:11:46.382204Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:46.382204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker Embedding Informed Audiovisual Active Speaker Detection for Egocentric Recordings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Jason Clarke, Stefan Goetze, Yoshihiko Gotoh","submitted_at":"2025-02-09T20:06:42Z","abstract_excerpt":"Audiovisual active speaker detection (ASD) addresses the task of determining the speech activity of a candidate speaker given acoustic and visual data. Typically, systems model the temporal correspondence of audiovisual cues, such as the synchronisation between speech and lip movement. Recent work has explored extending this paradigm by additionally leveraging speaker embeddings extracted from candidate speaker reference speech. This paper proposes the speaker comparison auxiliary network (SCAN) which uses speaker-specific information from both reference speech and the candidate audio signal t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06012","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/2502.06012/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":"2502.06012","created_at":"2026-07-05T10:11:46.382255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06012v1","created_at":"2026-07-05T10:11:46.382255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06012","created_at":"2026-07-05T10:11:46.382255+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFEVFR6ETYI4","created_at":"2026-07-05T10:11:46.382255+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFEVFR6ETYI4T2ZT","created_at":"2026-07-05T10:11:46.382255+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFEVFR6E","created_at":"2026-07-05T10:11:46.382255+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/PFEVFR6ETYI4T2ZT6AY6KK263W","json":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W.json","graph_json":"https://pith.science/api/pith-number/PFEVFR6ETYI4T2ZT6AY6KK263W/graph.json","events_json":"https://pith.science/api/pith-number/PFEVFR6ETYI4T2ZT6AY6KK263W/events.json","paper":"https://pith.science/paper/PFEVFR6E"},"agent_actions":{"view_html":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W","download_json":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W.json","view_paper":"https://pith.science/paper/PFEVFR6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06012&json=true","fetch_graph":"https://pith.science/api/pith-number/PFEVFR6ETYI4T2ZT6AY6KK263W/graph.json","fetch_events":"https://pith.science/api/pith-number/PFEVFR6ETYI4T2ZT6AY6KK263W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W/action/storage_attestation","attest_author":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W/action/author_attestation","sign_citation":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W/action/citation_signature","submit_replication":"https://pith.science/pith/PFEVFR6ETYI4T2ZT6AY6KK263W/action/replication_record"}},"created_at":"2026-07-05T10:11:46.382255+00:00","updated_at":"2026-07-05T10:11:46.382255+00:00"}