{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DQU6M2XPU3BYLED2WVSHPO2NSI","short_pith_number":"pith:DQU6M2XP","schema_version":"1.0","canonical_sha256":"1c29e66aefa6c385907ab56477bb4d920ce2e7a48a4adf27e7b3963c32fdaf87","source":{"kind":"arxiv","id":"2104.04784","version":2},"attestation_state":"computed","paper":{"title":"Lip reading using external viseme decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hossein Zeinali, Javad Peymanfard, Mohammad Reza Mohammadi, Nasser Mozayani","submitted_at":"2021-04-10T14:49:11Z","abstract_excerpt":"Lip-reading is the operation of recognizing speech from lip movements. This is a difficult task because the movements of the lips when pronouncing the words are similar for some of them. Viseme is used to describe lip movements during a conversation. This paper aims to show how to use external text data (for viseme-to-character mapping) by dividing video-to-character into two stages, namely converting video to viseme, and then converting viseme to character by using separate models. Our proposed method improves word error rate by 4\\% compared to the normal sequence to sequence lip-reading mode"},"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":"2104.04784","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-10T14:49:11Z","cross_cats_sorted":[],"title_canon_sha256":"54e4712d73f42b7461ff0ef6c1901fd0d0462c139860fc6c297deb608b0722c7","abstract_canon_sha256":"f1499c3a3fdad7eecf9aa82c8d58c9d6bff41b22850eb240761ffa2be29ca045"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:48.255277Z","signature_b64":"gr1LjHjjAfkxf5NU00VcdcxoCucwdZEpu1g9Shq8SC+biebHoSli8NpVnzCQ5qg8/tcNpQv3R3D5CgQ6vPLSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c29e66aefa6c385907ab56477bb4d920ce2e7a48a4adf27e7b3963c32fdaf87","last_reissued_at":"2026-07-05T03:29:48.254802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:48.254802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lip reading using external viseme decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hossein Zeinali, Javad Peymanfard, Mohammad Reza Mohammadi, Nasser Mozayani","submitted_at":"2021-04-10T14:49:11Z","abstract_excerpt":"Lip-reading is the operation of recognizing speech from lip movements. This is a difficult task because the movements of the lips when pronouncing the words are similar for some of them. Viseme is used to describe lip movements during a conversation. This paper aims to show how to use external text data (for viseme-to-character mapping) by dividing video-to-character into two stages, namely converting video to viseme, and then converting viseme to character by using separate models. Our proposed method improves word error rate by 4\\% compared to the normal sequence to sequence lip-reading mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04784","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.04784/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":"2104.04784","created_at":"2026-07-05T03:29:48.254861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04784v2","created_at":"2026-07-05T03:29:48.254861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04784","created_at":"2026-07-05T03:29:48.254861+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQU6M2XPU3BY","created_at":"2026-07-05T03:29:48.254861+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQU6M2XPU3BYLED2","created_at":"2026-07-05T03:29:48.254861+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQU6M2XP","created_at":"2026-07-05T03:29:48.254861+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/DQU6M2XPU3BYLED2WVSHPO2NSI","json":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI.json","graph_json":"https://pith.science/api/pith-number/DQU6M2XPU3BYLED2WVSHPO2NSI/graph.json","events_json":"https://pith.science/api/pith-number/DQU6M2XPU3BYLED2WVSHPO2NSI/events.json","paper":"https://pith.science/paper/DQU6M2XP"},"agent_actions":{"view_html":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI","download_json":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI.json","view_paper":"https://pith.science/paper/DQU6M2XP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04784&json=true","fetch_graph":"https://pith.science/api/pith-number/DQU6M2XPU3BYLED2WVSHPO2NSI/graph.json","fetch_events":"https://pith.science/api/pith-number/DQU6M2XPU3BYLED2WVSHPO2NSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI/action/storage_attestation","attest_author":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI/action/author_attestation","sign_citation":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI/action/citation_signature","submit_replication":"https://pith.science/pith/DQU6M2XPU3BYLED2WVSHPO2NSI/action/replication_record"}},"created_at":"2026-07-05T03:29:48.254861+00:00","updated_at":"2026-07-05T03:29:48.254861+00:00"}