{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H6DURN3CFYBM2VHXY42TBKRO7N","short_pith_number":"pith:H6DURN3C","schema_version":"1.0","canonical_sha256":"3f8748b7622e02cd54f7c73530aa2efb4ddce3a1891a40331086802f29fa3c21","source":{"kind":"arxiv","id":"1807.05162","version":3},"attestation_state":"computed","paper":{"title":"Large-Scale Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Senior, Ben Coppin, Ben Laurie, Brendan Shillingford, C\\'ian Hughes, Hank Liao, Hasim Sak, Kanishka Rao, Lorrayne Bennett, Marie Mulville, Matthew W. Hoffman, Nando de Freitas, Thomas Paine, Utsav Prabhu, Yannis Assael","submitted_at":"2018-07-13T16:21:34Z","abstract_excerpt":"This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking (3,886 hours of video). In tandem, we designed and trained an integrated lipreading system, consisting of a video processing pipeline that maps raw video to stable videos of lips and sequences of phonemes, a scalable deep neural network that maps the lip videos to sequences of phoneme distributions, and a production-level speech decoder that outputs sequences of "},"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":"1807.05162","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-13T16:21:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c6f13d68c5f268b7364d866100da201508edabb8efe9776950f67c4beec8adc6","abstract_canon_sha256":"15ed6ee543e057fbc3a6e15470eaff0b242ef9a7465f9ae57042a60c9cab4261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:29.575255Z","signature_b64":"DVyn0WSaOTNWOTTcHAD9Gn0FBSXZoWogkHwAwULVe5htZxzJlwYwDuVdRvmHfNJ4//qIV/09CDEekwkyoyBGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8748b7622e02cd54f7c73530aa2efb4ddce3a1891a40331086802f29fa3c21","last_reissued_at":"2026-05-18T00:04:29.574825Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:29.574825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Visual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andrew Senior, Ben Coppin, Ben Laurie, Brendan Shillingford, C\\'ian Hughes, Hank Liao, Hasim Sak, Kanishka Rao, Lorrayne Bennett, Marie Mulville, Matthew W. Hoffman, Nando de Freitas, Thomas Paine, Utsav Prabhu, Yannis Assael","submitted_at":"2018-07-13T16:21:34Z","abstract_excerpt":"This work presents a scalable solution to open-vocabulary visual speech recognition. To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking (3,886 hours of video). In tandem, we designed and trained an integrated lipreading system, consisting of a video processing pipeline that maps raw video to stable videos of lips and sequences of phonemes, a scalable deep neural network that maps the lip videos to sequences of phoneme distributions, and a production-level speech decoder that outputs sequences of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05162","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":""},"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":"1807.05162","created_at":"2026-05-18T00:04:29.574891+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05162v3","created_at":"2026-05-18T00:04:29.574891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05162","created_at":"2026-05-18T00:04:29.574891+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6DURN3CFYBM","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6DURN3CFYBM2VHX","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6DURN3C","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12170","citing_title":"LipReading with 3D-2D-CNN BLSTM-HMM and word-CTC models","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N","json":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N.json","graph_json":"https://pith.science/api/pith-number/H6DURN3CFYBM2VHXY42TBKRO7N/graph.json","events_json":"https://pith.science/api/pith-number/H6DURN3CFYBM2VHXY42TBKRO7N/events.json","paper":"https://pith.science/paper/H6DURN3C"},"agent_actions":{"view_html":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N","download_json":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N.json","view_paper":"https://pith.science/paper/H6DURN3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05162&json=true","fetch_graph":"https://pith.science/api/pith-number/H6DURN3CFYBM2VHXY42TBKRO7N/graph.json","fetch_events":"https://pith.science/api/pith-number/H6DURN3CFYBM2VHXY42TBKRO7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N/action/storage_attestation","attest_author":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N/action/author_attestation","sign_citation":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N/action/citation_signature","submit_replication":"https://pith.science/pith/H6DURN3CFYBM2VHXY42TBKRO7N/action/replication_record"}},"created_at":"2026-05-18T00:04:29.574891+00:00","updated_at":"2026-05-18T00:04:29.574891+00:00"}