{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5EUM4EQVLH3G6EOKGZIZRWJWUS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b23a8ede87bea3511200a2012cf325550767de420140e6a50ddb4e979a920d9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","title_canon_sha256":"3cdbf4cee0d4fac861f53858ecdedc24c910ce04bcadc239d6ae12b7da97a102"},"schema_version":"1.0","source":{"id":"2407.17902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17902","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17902v1","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17902","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_12","alias_value":"5EUM4EQVLH3G","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_16","alias_value":"5EUM4EQVLH3G6EOK","created_at":"2026-07-05T08:48:23Z"},{"alias_kind":"pith_short_8","alias_value":"5EUM4EQV","created_at":"2026-07-05T08:48:23Z"}],"graph_snapshots":[{"event_id":"sha256:8d0d1e2321186f7bce2cead0041c05f2e6a1cfd0843c710ed655a5daef4f026d","target":"graph","created_at":"2026-07-05T08:48:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.17902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The human brain has the capability to associate the unknown person's voice and face by leveraging their general relationship, referred to as ``cross-modal speaker verification''. This task poses significant challenges due to the complex relationship between the modalities. In this paper, we propose a ``Multi-stage Face-voice Association Learning with Keynote Speaker Diarization''~(MFV-KSD) framework. MFV-KSD contains a keynote speaker diarization front-end to effectively address the noisy speech inputs issue. To balance and enhance the intra-modal feature learning and inter-modal correlation u","authors_text":"Duc-Tuan Truong, Eng-Siong Chng, Haizhou Li, Massimo Alioto, Ruijie Tao, Yidi Jiang, Zhan Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","title":"Multi-Stage Face-Voice Association Learning with Keynote Speaker Diarization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17902","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5ce2ecc06f97041a07ff6d889e134e88501c0c1c6671451e1a7231b2d5f7fa25","target":"record","created_at":"2026-07-05T08:48:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b23a8ede87bea3511200a2012cf325550767de420140e6a50ddb4e979a920d9c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-25T09:46:04Z","title_canon_sha256":"3cdbf4cee0d4fac861f53858ecdedc24c910ce04bcadc239d6ae12b7da97a102"},"schema_version":"1.0","source":{"id":"2407.17902","kind":"arxiv","version":1}},"canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e928ce121559f66f11ca365198d936a4bd7fb13dce8547065915b7910ec9fffd","first_computed_at":"2026-07-05T08:48:23.236999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:23.236999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VMwaeqDONsj+AHrHBpm5QskGijhKpI1dKHPZwkTNnGHNAg16s/pFu9n8JLn1nKapYjCA+ubAlCUnLaENEa4kBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:23.237481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ce2ecc06f97041a07ff6d889e134e88501c0c1c6671451e1a7231b2d5f7fa25","sha256:8d0d1e2321186f7bce2cead0041c05f2e6a1cfd0843c710ed655a5daef4f026d"],"state_sha256":"2f9e5677999cd513a93a21724724d1f9c31d0c96c979c3b0b413859b8f15324a"}