{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QDTQHBVAMWVTSFSCXZUV4A4WMS","short_pith_number":"pith:QDTQHBVA","schema_version":"1.0","canonical_sha256":"80e70386a065ab391642be695e039664926722c1315b39875d4c64226ca48764","source":{"kind":"arxiv","id":"1809.02108","version":2},"attestation_state":"computed","paper":{"title":"Deep Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Senior, Andrew Zisserman, Joon Son Chung, Oriol Vinyals, Triantafyllos Afouras","submitted_at":"2018-09-06T17:34:27Z","abstract_excerpt":"The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is compl"},"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":"1809.02108","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-06T17:34:27Z","cross_cats_sorted":[],"title_canon_sha256":"6a919d5e8a92c2341abaac3a3e15c5013d656fe318444ce0df972dc94a8f2ae4","abstract_canon_sha256":"37faef2e35a926208d4d21bb8696bfd9ee19a3991f1cffe281a2255d64c544c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:31.409934Z","signature_b64":"sNGmU8oWzx1VIFqiNo5U3yN4fDJAmWCBHCtVy/eC6QDiI4jyfib4jqeu6Pz8KQnWmXI9Tm3zzgqONunWp2rkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e70386a065ab391642be695e039664926722c1315b39875d4c64226ca48764","last_reissued_at":"2026-05-17T23:57:31.409354Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:31.409354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Audio-Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Senior, Andrew Zisserman, Joon Son Chung, Oriol Vinyals, Triantafyllos Afouras","submitted_at":"2018-09-06T17:34:27Z","abstract_excerpt":"The goal of this work is to recognise phrases and sentences being spoken by a talking face, with or without the audio. Unlike previous works that have focussed on recognising a limited number of words or phrases, we tackle lip reading as an open-world problem - unconstrained natural language sentences, and in the wild videos. Our key contributions are: (1) we compare two models for lip reading, one using a CTC loss, and the other using a sequence-to-sequence loss. Both models are built on top of the transformer self-attention architecture; (2) we investigate to what extent lip reading is compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.02108","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.02108","created_at":"2026-05-17T23:57:31.409450+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.02108v2","created_at":"2026-05-17T23:57:31.409450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.02108","created_at":"2026-05-17T23:57:31.409450+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDTQHBVAMWVT","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDTQHBVAMWVTSFSC","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDTQHBVA","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16918","citing_title":"HighSync: High-Quality Lip Synchronization via Latent Diffusion Models","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS","json":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS.json","graph_json":"https://pith.science/api/pith-number/QDTQHBVAMWVTSFSCXZUV4A4WMS/graph.json","events_json":"https://pith.science/api/pith-number/QDTQHBVAMWVTSFSCXZUV4A4WMS/events.json","paper":"https://pith.science/paper/QDTQHBVA"},"agent_actions":{"view_html":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS","download_json":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS.json","view_paper":"https://pith.science/paper/QDTQHBVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.02108&json=true","fetch_graph":"https://pith.science/api/pith-number/QDTQHBVAMWVTSFSCXZUV4A4WMS/graph.json","fetch_events":"https://pith.science/api/pith-number/QDTQHBVAMWVTSFSCXZUV4A4WMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS/action/storage_attestation","attest_author":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS/action/author_attestation","sign_citation":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS/action/citation_signature","submit_replication":"https://pith.science/pith/QDTQHBVAMWVTSFSCXZUV4A4WMS/action/replication_record"}},"created_at":"2026-05-17T23:57:31.409450+00:00","updated_at":"2026-05-17T23:57:31.409450+00:00"}