{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WRULFOFK663MAZFRUVAUIQCHX4","short_pith_number":"pith:WRULFOFK","schema_version":"1.0","canonical_sha256":"b468b2b8aaf7b6c064b1a541444047bf25bd8c10717e43710d9a265b735966f1","source":{"kind":"arxiv","id":"2201.01763","version":3},"attestation_state":"computed","paper":{"title":"Robust Self-Supervised Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Abdelrahman Mohamed, Bowen Shi, Wei-Ning Hsu","submitted_at":"2022-01-05T18:50:50Z","abstract_excerpt":"Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker. However, previous AVSR work focused solely on the supervised learning setup; hence the progress was hindered by the amount of labeled data available. In this work, we present a self-supervis"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.01763","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-05T18:50:50Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"7ea86b842dd070ae431d35349159216829aab835d397352416c5fc5cf6107cd6","abstract_canon_sha256":"a17819ce5d3b7593b893a530017cedc5d10792a63e66ba87f49f39b434fc578e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:25.184553Z","signature_b64":"VCzPfWrFpewMX92CBY7O3FCtucUp85D1ajDGJUUiMwOkQkzVXimR1zfhKJPMNeEx+l7pJ4nrBKh2z7tCBW4rDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b468b2b8aaf7b6c064b1a541444047bf25bd8c10717e43710d9a265b735966f1","last_reissued_at":"2026-07-05T04:40:25.184031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:25.184031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Self-Supervised Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Abdelrahman Mohamed, Bowen Shi, Wei-Ning Hsu","submitted_at":"2022-01-05T18:50:50Z","abstract_excerpt":"Audio-based automatic speech recognition (ASR) degrades significantly in noisy environments and is particularly vulnerable to interfering speech, as the model cannot determine which speaker to transcribe. Audio-visual speech recognition (AVSR) systems improve robustness by complementing the audio stream with the visual information that is invariant to noise and helps the model focus on the desired speaker. However, previous AVSR work focused solely on the supervised learning setup; hence the progress was hindered by the amount of labeled data available. In this work, we present a self-supervis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01763","kind":"arxiv","version":3},"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/2201.01763/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2201.01763","created_at":"2026-07-05T04:40:25.184091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01763v3","created_at":"2026-07-05T04:40:25.184091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01763","created_at":"2026-07-05T04:40:25.184091+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRULFOFK663M","created_at":"2026-07-05T04:40:25.184091+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRULFOFK663MAZFR","created_at":"2026-07-05T04:40:25.184091+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRULFOFK","created_at":"2026-07-05T04:40:25.184091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.07608","citing_title":"AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4","json":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4.json","graph_json":"https://pith.science/api/pith-number/WRULFOFK663MAZFRUVAUIQCHX4/graph.json","events_json":"https://pith.science/api/pith-number/WRULFOFK663MAZFRUVAUIQCHX4/events.json","paper":"https://pith.science/paper/WRULFOFK"},"agent_actions":{"view_html":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4","download_json":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4.json","view_paper":"https://pith.science/paper/WRULFOFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01763&json=true","fetch_graph":"https://pith.science/api/pith-number/WRULFOFK663MAZFRUVAUIQCHX4/graph.json","fetch_events":"https://pith.science/api/pith-number/WRULFOFK663MAZFRUVAUIQCHX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4/action/storage_attestation","attest_author":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4/action/author_attestation","sign_citation":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4/action/citation_signature","submit_replication":"https://pith.science/pith/WRULFOFK663MAZFRUVAUIQCHX4/action/replication_record"}},"created_at":"2026-07-05T04:40:25.184091+00:00","updated_at":"2026-07-05T04:40:25.184091+00:00"}