{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J7RRMFVYXILGZRKJDYP4IQNQ2A","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":"900888096a3c38bbe99619e3ee695ac9a4d07ad6738d34b5827e35447cb235e9","cross_cats_sorted":["cs.ET","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-29T02:38:56Z","title_canon_sha256":"fa1ce44eeb446671c05893cc43d9c0926cd01e29896b558710c4b3f7718535d4"},"schema_version":"1.0","source":{"id":"2507.21448","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21448","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21448v2","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21448","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"pith_short_12","alias_value":"J7RRMFVYXILG","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"pith_short_16","alias_value":"J7RRMFVYXILGZRKJ","created_at":"2026-07-05T11:48:06Z"},{"alias_kind":"pith_short_8","alias_value":"J7RRMFVY","created_at":"2026-07-05T11:48:06Z"}],"graph_snapshots":[{"event_id":"sha256:3d0be1cdc8a3dfa6d1e177bde556d9a6b7c7eff9fd910e0cc42a6853018aa028","target":"graph","created_at":"2026-07-05T11:48:06Z","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/2507.21448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech enhancement in audio-only settings remains challenging, particularly in the presence of interfering speakers. This paper presents a simple yet effective real-time audio-visual speech enhancement (AVSE) system, RAVEN, which isolates and enhances the on-screen target speaker while suppressing interfering speakers and background noise. We investigate how visual embeddings learned from audio-visual speech recognition (AVSR) and active speaker detection (ASD) contribute to AVSE across different SNR conditions and numbers of interfering speakers. Our results show concatenating embeddings from","authors_text":"Li-Chia Yang, Shuo Zhang, Sile Yin, T. Aleksandra Ma","cross_cats":["cs.ET","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-29T02:38:56Z","title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21448","kind":"arxiv","version":2},"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":"sha256:89853ae930348ff14370292d87a023ffdbf3b60162fb9cd442fa78d91fdbec1a","target":"record","created_at":"2026-07-05T11:48:06Z","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":"900888096a3c38bbe99619e3ee695ac9a4d07ad6738d34b5827e35447cb235e9","cross_cats_sorted":["cs.ET","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-07-29T02:38:56Z","title_canon_sha256":"fa1ce44eeb446671c05893cc43d9c0926cd01e29896b558710c4b3f7718535d4"},"schema_version":"1.0","source":{"id":"2507.21448","kind":"arxiv","version":2}},"canonical_sha256":"4fe31616b8ba166cc5491e1fc441b0d018078c61faff09efe9464afcd4340eca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4fe31616b8ba166cc5491e1fc441b0d018078c61faff09efe9464afcd4340eca","first_computed_at":"2026-07-05T11:48:06.217487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:06.217487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o9EpoUHsiUL1/W41jNfjhMeHwKADA4I0QLbrNqGVwhKeifLmAbR7+QypvG9VN1How1qJh3T8/xQJVAjket8AAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:06.217982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21448","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89853ae930348ff14370292d87a023ffdbf3b60162fb9cd442fa78d91fdbec1a","sha256:3d0be1cdc8a3dfa6d1e177bde556d9a6b7c7eff9fd910e0cc42a6853018aa028"],"state_sha256":"2fe65597abd4b5d02730e310883409a1ac252884d52b3335df360d0ec74fecd5"}