{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RBK3RDXWQUMHDDGEUGQZBLS4M4","short_pith_number":"pith:RBK3RDXW","canonical_record":{"source":{"id":"2207.06020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T08:07:19Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS","eess.IV"],"title_canon_sha256":"0680c50bf1f165663ab9dcaf51a77cf868350b0db196e23b413159657dfa730f","abstract_canon_sha256":"d20c2aba23644161363418ac5a310b892aee86c2e51453ecf4c25dd0d296c007"},"schema_version":"1.0"},"canonical_sha256":"8855b88ef68518718cc4a1a190ae5c672002f20f0b19b8acab3f78563a8b753c","source":{"kind":"arxiv","id":"2207.06020","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RBK3RDXWQUMHDDGEUGQZBLS4M4","target":"record","payload":{"canonical_record":{"source":{"id":"2207.06020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-07-13T08:07:19Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","eess.AS","eess.IV"],"title_canon_sha256":"0680c50bf1f165663ab9dcaf51a77cf868350b0db196e23b413159657dfa730f","abstract_canon_sha256":"d20c2aba23644161363418ac5a310b892aee86c2e51453ecf4c25dd0d296c007"},"schema_version":"1.0"},"canonical_sha256":"8855b88ef68518718cc4a1a190ae5c672002f20f0b19b8acab3f78563a8b753c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:39:53.858634Z","signature_b64":"uXQ6hCAaQYFqpRL5/DHHvTOo6Nr45KGxMCZJ+ZBSHT6UhJQ+c+/ITErIFtMGpu1sYIh8Fg2A4NbLgpd8vjTrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8855b88ef68518718cc4a1a190ae5c672002f20f0b19b8acab3f78563a8b753c","last_reissued_at":"2026-07-05T04:39:53.858245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:39:53.858245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.06020","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:39:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hf3Tw1v6SZF5NkPz5YjmJPC9B5RZ0pe6S8FMtM4E036WdRj+BZLSP+wpbW4BGYxiBZ1PXphAgcNZT8dkda8GCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:16.155392Z"},"content_sha256":"1c7f30481e6e0a4ae680e721f51bdd59fcdd106d8120106750211e2423e3c106","schema_version":"1.0","event_id":"sha256:1c7f30481e6e0a4ae680e721f51bdd59fcdd106d8120106750211e2423e3c106"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RBK3RDXWQUMHDDGEUGQZBLS4M4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","eess.AS","eess.IV"],"primary_cat":"cs.SD","authors_text":"Daehun Yoo, Joanna Hong, Minsu Kim, Yong Man Ro","submitted_at":"2022-07-13T08:07:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06020","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/2207.06020/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:39:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJ/5dDXMwkib/0+HJ4ZbyZ1UqN6P+bLnI8P3pV8d8EEdcbLGWksjWKic3T+Rf7U+TJtXhdygJDSM5sSde013Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:32:16.155963Z"},"content_sha256":"050ae2bfa51e292e1ea8ab66382e534c66f2c3834e1292ef20249c1ea5e09232","schema_version":"1.0","event_id":"sha256:050ae2bfa51e292e1ea8ab66382e534c66f2c3834e1292ef20249c1ea5e09232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4/bundle.json","state_url":"https://pith.science/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T03:32:16Z","links":{"resolver":"https://pith.science/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4","bundle":"https://pith.science/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4/bundle.json","state":"https://pith.science/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBK3RDXWQUMHDDGEUGQZBLS4M4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5XBUiCKhtup3n6iNXsyQ/b+AtbwO4XNUXv7Xbv9SxHku6lm97l6FY1G06noL3TvYB8G7B/vBi4uspJV5uhMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:32:16.163915Z","bundle_sha256":"c4336c985105872db3204beca4a30aee159ca3175cb00f7e463a62a588dde0c1"}}