{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CKU6HXUCW23M4KOK7VQHVXOJB7","short_pith_number":"pith:CKU6HXUC","schema_version":"1.0","canonical_sha256":"12a9e3de82b6b6ce29cafd607addc90ffddf42cec7f989793bed517b8939ac43","source":{"kind":"arxiv","id":"1806.06053","version":1},"attestation_state":"computed","paper":{"title":"Deep Lip Reading: a comparison of models and an online application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Joon Son Chung, Triantafyllos Afouras","submitted_at":"2018-06-15T17:37:01Z","abstract_excerpt":"The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully convolutional model; and (iii) the recently proposed transformer model. The recurrent and fully convolutional models are trained with a Connectionist Temporal Classification loss and use an explicit language model for decoding, the transformer is a sequence-to-sequence model. Our best performing model improves the state-of-the-art word error rate on the challenging"},"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":"1806.06053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-06-15T17:37:01Z","cross_cats_sorted":[],"title_canon_sha256":"ef734b188f9d105cf361737fb85d27a24a12ffe5b5f3e7c342dacba0267fcc34","abstract_canon_sha256":"ec88e4d801864064bae092098db99b5104b120143ab14d2039355bb4d6b6e480"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:08.590816Z","signature_b64":"KiJ1JC7Szwh9jFrJB5dCFjblv6w47jEqcp/HcS7k2VtzKJN/ZE8nretR7UsjA1Mr8tVAlB736PNwZKSDB/+bAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12a9e3de82b6b6ce29cafd607addc90ffddf42cec7f989793bed517b8939ac43","last_reissued_at":"2026-05-18T00:13:08.590249Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:08.590249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Lip Reading: a comparison of models and an online application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Joon Son Chung, Triantafyllos Afouras","submitted_at":"2018-06-15T17:37:01Z","abstract_excerpt":"The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully convolutional model; and (iii) the recently proposed transformer model. The recurrent and fully convolutional models are trained with a Connectionist Temporal Classification loss and use an explicit language model for decoding, the transformer is a sequence-to-sequence model. Our best performing model improves the state-of-the-art word error rate on the challenging"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06053","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":""},"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":"1806.06053","created_at":"2026-05-18T00:13:08.590332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06053v1","created_at":"2026-05-18T00:13:08.590332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06053","created_at":"2026-05-18T00:13:08.590332+00:00"},{"alias_kind":"pith_short_12","alias_value":"CKU6HXUCW23M","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CKU6HXUCW23M4KOK","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CKU6HXUC","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7","json":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7.json","graph_json":"https://pith.science/api/pith-number/CKU6HXUCW23M4KOK7VQHVXOJB7/graph.json","events_json":"https://pith.science/api/pith-number/CKU6HXUCW23M4KOK7VQHVXOJB7/events.json","paper":"https://pith.science/paper/CKU6HXUC"},"agent_actions":{"view_html":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7","download_json":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7.json","view_paper":"https://pith.science/paper/CKU6HXUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06053&json=true","fetch_graph":"https://pith.science/api/pith-number/CKU6HXUCW23M4KOK7VQHVXOJB7/graph.json","fetch_events":"https://pith.science/api/pith-number/CKU6HXUCW23M4KOK7VQHVXOJB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7/action/storage_attestation","attest_author":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7/action/author_attestation","sign_citation":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7/action/citation_signature","submit_replication":"https://pith.science/pith/CKU6HXUCW23M4KOK7VQHVXOJB7/action/replication_record"}},"created_at":"2026-05-18T00:13:08.590332+00:00","updated_at":"2026-05-18T00:13:08.590332+00:00"}