{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XW53S7MTSUCFKI4K3JA3CPHTWR","short_pith_number":"pith:XW53S7MT","schema_version":"1.0","canonical_sha256":"bdbbb97d93950455238ada41b13cf3b44fcfcd2824fef1bc5ebbf5061f42b385","source":{"kind":"arxiv","id":"2306.03258","version":2},"attestation_state":"computed","paper":{"title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Aviv Shamsian, Ethan Fetaya, Lior Bracha, Sharon Gannot, Yochai Yemini","submitted_at":"2023-06-05T21:20:33Z","abstract_excerpt":"Lip-to-speech involves generating a natural-sounding speech synchronized with a soundless video of a person talking. Despite recent advances, current methods still cannot produce high-quality speech with high levels of intelligibility for challenging and realistic datasets such as LRS3. In this work, we present LipVoicer, a novel method that generates high-quality speech, even for in-the-wild and rich datasets, by incorporating the text modality. Given a silent video, we first predict the spoken text using a pre-trained lip-reading network. We then condition a diffusion model on the video and "},"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":"2306.03258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-05T21:20:33Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5f9e5087411c1d98990ea24cca67b0044177b53dc3b4c73c45846fdeae8d3d35","abstract_canon_sha256":"e4ce32b204deb0db9826ac8faadb66e71f127c89a1c315813a5e19812291411e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:30.480942Z","signature_b64":"1BYGUoBXcdA/RzQlUXAoPoI7D09BhkW/KmLcxuSimEEOmXf5MsFzO2NwJ40t4Y58CScpYfqdnS/ocHKjzbu8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdbbb97d93950455238ada41b13cf3b44fcfcd2824fef1bc5ebbf5061f42b385","last_reissued_at":"2026-07-05T08:01:30.480495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:30.480495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Aviv Shamsian, Ethan Fetaya, Lior Bracha, Sharon Gannot, Yochai Yemini","submitted_at":"2023-06-05T21:20:33Z","abstract_excerpt":"Lip-to-speech involves generating a natural-sounding speech synchronized with a soundless video of a person talking. Despite recent advances, current methods still cannot produce high-quality speech with high levels of intelligibility for challenging and realistic datasets such as LRS3. In this work, we present LipVoicer, a novel method that generates high-quality speech, even for in-the-wild and rich datasets, by incorporating the text modality. Given a silent video, we first predict the spoken text using a pre-trained lip-reading network. We then condition a diffusion model on the video and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03258","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/2306.03258/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":"2306.03258","created_at":"2026-07-05T08:01:30.480552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03258v2","created_at":"2026-07-05T08:01:30.480552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03258","created_at":"2026-07-05T08:01:30.480552+00:00"},{"alias_kind":"pith_short_12","alias_value":"XW53S7MTSUCF","created_at":"2026-07-05T08:01:30.480552+00:00"},{"alias_kind":"pith_short_16","alias_value":"XW53S7MTSUCFKI4K","created_at":"2026-07-05T08:01:30.480552+00:00"},{"alias_kind":"pith_short_8","alias_value":"XW53S7MT","created_at":"2026-07-05T08:01:30.480552+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/XW53S7MTSUCFKI4K3JA3CPHTWR","json":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR.json","graph_json":"https://pith.science/api/pith-number/XW53S7MTSUCFKI4K3JA3CPHTWR/graph.json","events_json":"https://pith.science/api/pith-number/XW53S7MTSUCFKI4K3JA3CPHTWR/events.json","paper":"https://pith.science/paper/XW53S7MT"},"agent_actions":{"view_html":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR","download_json":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR.json","view_paper":"https://pith.science/paper/XW53S7MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03258&json=true","fetch_graph":"https://pith.science/api/pith-number/XW53S7MTSUCFKI4K3JA3CPHTWR/graph.json","fetch_events":"https://pith.science/api/pith-number/XW53S7MTSUCFKI4K3JA3CPHTWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR/action/storage_attestation","attest_author":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR/action/author_attestation","sign_citation":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR/action/citation_signature","submit_replication":"https://pith.science/pith/XW53S7MTSUCFKI4K3JA3CPHTWR/action/replication_record"}},"created_at":"2026-07-05T08:01:30.480552+00:00","updated_at":"2026-07-05T08:01:30.480552+00:00"}