{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XW53S7MTSUCFKI4K3JA3CPHTWR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4ce32b204deb0db9826ac8faadb66e71f127c89a1c315813a5e19812291411e","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-05T21:20:33Z","title_canon_sha256":"5f9e5087411c1d98990ea24cca67b0044177b53dc3b4c73c45846fdeae8d3d35"},"schema_version":"1.0","source":{"id":"2306.03258","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03258","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03258v2","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03258","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"XW53S7MTSUCF","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"XW53S7MTSUCFKI4K","created_at":"2026-07-05T08:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"XW53S7MT","created_at":"2026-07-05T08:01:30Z"}],"graph_snapshots":[{"event_id":"sha256:9a26b682aed2760f6cf76959c82670671d4c2480a0e4d41e05b35a7fc12ad2f9","target":"graph","created_at":"2026-07-05T08:01:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.03258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Aviv Shamsian, Ethan Fetaya, Lior Bracha, Sharon Gannot, Yochai Yemini","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-05T21:20:33Z","title":"LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03258","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2afdf1ec3a718a47e68476336fefcc8f2621f8239d505c7295254018a974e2b9","target":"record","created_at":"2026-07-05T08:01:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4ce32b204deb0db9826ac8faadb66e71f127c89a1c315813a5e19812291411e","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-06-05T21:20:33Z","title_canon_sha256":"5f9e5087411c1d98990ea24cca67b0044177b53dc3b4c73c45846fdeae8d3d35"},"schema_version":"1.0","source":{"id":"2306.03258","kind":"arxiv","version":2}},"canonical_sha256":"bdbbb97d93950455238ada41b13cf3b44fcfcd2824fef1bc5ebbf5061f42b385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdbbb97d93950455238ada41b13cf3b44fcfcd2824fef1bc5ebbf5061f42b385","first_computed_at":"2026-07-05T08:01:30.480495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:30.480495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1BYGUoBXcdA/RzQlUXAoPoI7D09BhkW/KmLcxuSimEEOmXf5MsFzO2NwJ40t4Y58CScpYfqdnS/ocHKjzbu8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:30.480942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03258","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2afdf1ec3a718a47e68476336fefcc8f2621f8239d505c7295254018a974e2b9","sha256:9a26b682aed2760f6cf76959c82670671d4c2480a0e4d41e05b35a7fc12ad2f9"],"state_sha256":"a14a402a4d250d0782f0a82d4daa4813d2c1317be1131c5657b4e8f6b31addb4"}