{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:K2X3KFW3REGGG4DHCBGGZHCLK2","short_pith_number":"pith:K2X3KFW3","schema_version":"1.0","canonical_sha256":"56afb516db890c637067104c6c9c4b5697cd3bcfe56455ef85fadd8afa3849c6","source":{"kind":"arxiv","id":"1708.01204","version":3},"attestation_state":"computed","paper":{"title":"Improved Speech Reconstruction from Silent Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Ariel Ephrat, Shmuel Peleg, Tavi Halperin","submitted_at":"2017-08-01T18:01:08Z","abstract_excerpt":"Speechreading is the task of inferring phonetic information from visually observed articulatory facial movements, and is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible and natural-sounding acoustic speech signal from silent video frames of a speaking person. We train our model on speakers from the GRID and TCD-TIMIT datasets, and evaluate the quality and intelligibility of reconstructed speech using common objective measurements. We show that speech predictions from th"},"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":"1708.01204","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-01T18:01:08Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"90b59682ee570e0ac5bcb38a41b1e5a30169cf2cef37c603b5f3cd768828bddd","abstract_canon_sha256":"c8bce505a2ed17165c3a53f3b22295fe142e818666d28a07eef683bb508407d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:21.828080Z","signature_b64":"cjbpFyptLQjocKZWANDkG7lLgG0HFVboppEHvMls+YQVFEf4hXAMC/6JdHbh1+JrjzBfgsOpLpbHBpjfCGGNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56afb516db890c637067104c6c9c4b5697cd3bcfe56455ef85fadd8afa3849c6","last_reissued_at":"2026-05-18T00:36:21.827523Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:21.827523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Speech Reconstruction from Silent Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.CV","authors_text":"Ariel Ephrat, Shmuel Peleg, Tavi Halperin","submitted_at":"2017-08-01T18:01:08Z","abstract_excerpt":"Speechreading is the task of inferring phonetic information from visually observed articulatory facial movements, and is a notoriously difficult task for humans to perform. In this paper we present an end-to-end model based on a convolutional neural network (CNN) for generating an intelligible and natural-sounding acoustic speech signal from silent video frames of a speaking person. We train our model on speakers from the GRID and TCD-TIMIT datasets, and evaluate the quality and intelligibility of reconstructed speech using common objective measurements. We show that speech predictions from th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01204","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":"1708.01204","created_at":"2026-05-18T00:36:21.827587+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01204v3","created_at":"2026-05-18T00:36:21.827587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01204","created_at":"2026-05-18T00:36:21.827587+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2X3KFW3REGG","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2X3KFW3REGGG4DH","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2X3KFW3","created_at":"2026-05-18T12:31:24.725408+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/K2X3KFW3REGGG4DHCBGGZHCLK2","json":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2.json","graph_json":"https://pith.science/api/pith-number/K2X3KFW3REGGG4DHCBGGZHCLK2/graph.json","events_json":"https://pith.science/api/pith-number/K2X3KFW3REGGG4DHCBGGZHCLK2/events.json","paper":"https://pith.science/paper/K2X3KFW3"},"agent_actions":{"view_html":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2","download_json":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2.json","view_paper":"https://pith.science/paper/K2X3KFW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01204&json=true","fetch_graph":"https://pith.science/api/pith-number/K2X3KFW3REGGG4DHCBGGZHCLK2/graph.json","fetch_events":"https://pith.science/api/pith-number/K2X3KFW3REGGG4DHCBGGZHCLK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2/action/storage_attestation","attest_author":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2/action/author_attestation","sign_citation":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2/action/citation_signature","submit_replication":"https://pith.science/pith/K2X3KFW3REGGG4DHCBGGZHCLK2/action/replication_record"}},"created_at":"2026-05-18T00:36:21.827587+00:00","updated_at":"2026-05-18T00:36:21.827587+00:00"}