{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RBK3RDXWQUMHDDGEUGQZBLS4M4","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":"d20c2aba23644161363418ac5a310b892aee86c2e51453ecf4c25dd0d296c007","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T08:07:19Z","title_canon_sha256":"0680c50bf1f165663ab9dcaf51a77cf868350b0db196e23b413159657dfa730f"},"schema_version":"1.0","source":{"id":"2207.06020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.06020","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"arxiv_version","alias_value":"2207.06020v1","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06020","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"pith_short_12","alias_value":"RBK3RDXWQUMH","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"pith_short_16","alias_value":"RBK3RDXWQUMHDDGE","created_at":"2026-07-05T04:39:53Z"},{"alias_kind":"pith_short_8","alias_value":"RBK3RDXW","created_at":"2026-07-05T04:39:53Z"}],"graph_snapshots":[{"event_id":"sha256:050ae2bfa51e292e1ea8ab66382e534c66f2c3834e1292ef20249c1ea5e09232","target":"graph","created_at":"2026-07-05T04:39:53Z","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/2207.06020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper focuses on designing a noise-robust end-to-end Audio-Visual Speech Recognition (AVSR) system. To this end, we propose Visual Context-driven Audio Feature Enhancement module (V-CAFE) to enhance the input noisy audio speech with a help of audio-visual correspondence. The proposed V-CAFE is designed to capture the transition of lip movements, namely visual context and to generate a noise reduction mask by considering the obtained visual context. Through context-dependent modeling, the ambiguity in viseme-to-phoneme mapping can be refined for mask generation. The noisy representations a","authors_text":"Daehun Yoo, Joanna Hong, Minsu Kim, Yong Man Ro","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T08:07:19Z","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06020","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":"sha256:1c7f30481e6e0a4ae680e721f51bdd59fcdd106d8120106750211e2423e3c106","target":"record","created_at":"2026-07-05T04:39:53Z","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":"d20c2aba23644161363418ac5a310b892aee86c2e51453ecf4c25dd0d296c007","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T08:07:19Z","title_canon_sha256":"0680c50bf1f165663ab9dcaf51a77cf868350b0db196e23b413159657dfa730f"},"schema_version":"1.0","source":{"id":"2207.06020","kind":"arxiv","version":1}},"canonical_sha256":"8855b88ef68518718cc4a1a190ae5c672002f20f0b19b8acab3f78563a8b753c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8855b88ef68518718cc4a1a190ae5c672002f20f0b19b8acab3f78563a8b753c","first_computed_at":"2026-07-05T04:39:53.858245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:39:53.858245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXQ6hCAaQYFqpRL5/DHHvTOo6Nr45KGxMCZJ+ZBSHT6UhJQ+c+/ITErIFtMGpu1sYIh8Fg2A4NbLgpd8vjTrBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:39:53.858634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.06020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c7f30481e6e0a4ae680e721f51bdd59fcdd106d8120106750211e2423e3c106","sha256:050ae2bfa51e292e1ea8ab66382e534c66f2c3834e1292ef20249c1ea5e09232"],"state_sha256":"f1335aa5abfa1378f441c60a645cb5a775f8ff148a7606d609a1ffff66894dcb"}