{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YUCVYWJWLH23LMWDQZDLL2D6VS","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":"22a1155f631401bbf7b4745e49ce79b9e493467123313721fab83de83da2f36c","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T17:57:10Z","title_canon_sha256":"53e6c70b34f11fada3ce3602041e4f78f775e93c78d696b7e0d43566154bfd0a"},"schema_version":"1.0","source":{"id":"2203.17263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.17263","created_at":"2026-07-05T04:10:33Z"},{"alias_kind":"arxiv_version","alias_value":"2203.17263v1","created_at":"2026-07-05T04:10:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17263","created_at":"2026-07-05T04:10:33Z"},{"alias_kind":"pith_short_12","alias_value":"YUCVYWJWLH23","created_at":"2026-07-05T04:10:33Z"},{"alias_kind":"pith_short_16","alias_value":"YUCVYWJWLH23LMWD","created_at":"2026-07-05T04:10:33Z"},{"alias_kind":"pith_short_8","alias_value":"YUCVYWJW","created_at":"2026-07-05T04:10:33Z"}],"graph_snapshots":[{"event_id":"sha256:ebb92a647e90c3c9f915d499550bb64e34c8d16d17c6eeb287fadc56745d6486","target":"graph","created_at":"2026-07-05T04:10:33Z","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/2203.17263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since facial actions such as lip movements contain significant information about speech content, it is not surprising that audio-visual speech enhancement methods are more accurate than their audio-only counterparts. Yet, state-of-the-art approaches still struggle to generate clean, realistic speech without noise artifacts and unnatural distortions in challenging acoustic environments. In this paper, we propose a novel audio-visual speech enhancement framework for high-fidelity telecommunications in AR/VR. Our approach leverages audio-visual speech cues to generate the codes of a neural speech","authors_text":"Alexander Richard, Dejan Markovic, Karren Yang, Steven Krenn, Vasu Agrawal","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T17:57:10Z","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17263","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:c62ca658693870faf061171aeaa08179da37041b98c4ca0e9dc853f21469e390","target":"record","created_at":"2026-07-05T04:10:33Z","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":"22a1155f631401bbf7b4745e49ce79b9e493467123313721fab83de83da2f36c","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-31T17:57:10Z","title_canon_sha256":"53e6c70b34f11fada3ce3602041e4f78f775e93c78d696b7e0d43566154bfd0a"},"schema_version":"1.0","source":{"id":"2203.17263","kind":"arxiv","version":1}},"canonical_sha256":"c5055c593659f5b5b2c38646b5e87eac8e7402e870aa5673b87c7fab49ec0f49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5055c593659f5b5b2c38646b5e87eac8e7402e870aa5673b87c7fab49ec0f49","first_computed_at":"2026-07-05T04:10:33.079986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:33.079986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q/oRmeqwPb7JBJl2AJaV9ShnyTVvVl7aufcZqQ9AmjPZNpSBJBOs6y6Fa51TfR20bBwgNr6vS6MT3/JLLePvBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:33.080410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.17263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c62ca658693870faf061171aeaa08179da37041b98c4ca0e9dc853f21469e390","sha256:ebb92a647e90c3c9f915d499550bb64e34c8d16d17c6eeb287fadc56745d6486"],"state_sha256":"2409d253e24d9a50dda661b81c159bb7ace61ba6f173da4f9b30ebfd8ce938d5"}