{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HA57B45QQKS4DWB74RYR4XCSCU","short_pith_number":"pith:HA57B45Q","schema_version":"1.0","canonical_sha256":"383bf0f3b082a5c1d83fe4711e5c521518f3a064811ad5b413c168de80a7cf18","source":{"kind":"arxiv","id":"2206.04523","version":1},"attestation_state":"computed","paper":{"title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CL","authors_text":"Alexander Waibel, Alperen Kantarc{\\i}, Carlos Mullov, Dogucan Yaman, Fevziye Irem Eyiokur, Haz{\\i}m Kemal Ekenel, Mehmet Arif Demirtas, Moritz Behr, Stefan Constantin, Tuan-Nam Nguyen","submitted_at":"2022-06-09T14:15:37Z","abstract_excerpt":"In this paper, we propose a neural end-to-end system for voice preserving, lip-synchronous translation of videos. The system is designed to combine multiple component models and produces a video of the original speaker speaking in the target language that is lip-synchronous with the target speech, yet maintains emphases in speech, voice characteristics, face video of the original speaker. The pipeline starts with automatic speech recognition including emphasis detection, followed by a translation model. The translated text is then synthesized by a Text-to-Speech model that recreates the origin"},"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":"2206.04523","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-09T14:15:37Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS","eess.IV"],"title_canon_sha256":"cacc540c4b31a6970b52befa6fa8a828e06108c025764fa93d939d94bf7914fd","abstract_canon_sha256":"dbda82feb2f14666ff96e4ccc134a3d3c1808cd90c0c0a5f6d10d62b8b12c718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:34.670634Z","signature_b64":"6kGdAh6soeTP0SPthPtRllsJAtHt3U/KLYy/7eZU70Ezm1DHmZdxFMm512o31GvlVOq/S2otTeKSKtCHkZIOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"383bf0f3b082a5c1d83fe4711e5c521518f3a064811ad5b413c168de80a7cf18","last_reissued_at":"2026-07-05T04:30:34.670077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:34.670077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS","eess.IV"],"primary_cat":"cs.CL","authors_text":"Alexander Waibel, Alperen Kantarc{\\i}, Carlos Mullov, Dogucan Yaman, Fevziye Irem Eyiokur, Haz{\\i}m Kemal Ekenel, Mehmet Arif Demirtas, Moritz Behr, Stefan Constantin, Tuan-Nam Nguyen","submitted_at":"2022-06-09T14:15:37Z","abstract_excerpt":"In this paper, we propose a neural end-to-end system for voice preserving, lip-synchronous translation of videos. The system is designed to combine multiple component models and produces a video of the original speaker speaking in the target language that is lip-synchronous with the target speech, yet maintains emphases in speech, voice characteristics, face video of the original speaker. The pipeline starts with automatic speech recognition including emphasis detection, followed by a translation model. The translated text is then synthesized by a Text-to-Speech model that recreates the origin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04523","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.04523/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":"2206.04523","created_at":"2026-07-05T04:30:34.670136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04523v1","created_at":"2026-07-05T04:30:34.670136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04523","created_at":"2026-07-05T04:30:34.670136+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA57B45QQKS4","created_at":"2026-07-05T04:30:34.670136+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA57B45QQKS4DWB7","created_at":"2026-07-05T04:30:34.670136+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA57B45Q","created_at":"2026-07-05T04:30:34.670136+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/HA57B45QQKS4DWB74RYR4XCSCU","json":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU.json","graph_json":"https://pith.science/api/pith-number/HA57B45QQKS4DWB74RYR4XCSCU/graph.json","events_json":"https://pith.science/api/pith-number/HA57B45QQKS4DWB74RYR4XCSCU/events.json","paper":"https://pith.science/paper/HA57B45Q"},"agent_actions":{"view_html":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU","download_json":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU.json","view_paper":"https://pith.science/paper/HA57B45Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04523&json=true","fetch_graph":"https://pith.science/api/pith-number/HA57B45QQKS4DWB74RYR4XCSCU/graph.json","fetch_events":"https://pith.science/api/pith-number/HA57B45QQKS4DWB74RYR4XCSCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU/action/storage_attestation","attest_author":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU/action/author_attestation","sign_citation":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU/action/citation_signature","submit_replication":"https://pith.science/pith/HA57B45QQKS4DWB74RYR4XCSCU/action/replication_record"}},"created_at":"2026-07-05T04:30:34.670136+00:00","updated_at":"2026-07-05T04:30:34.670136+00:00"}