{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3SY7DGRF3532WH6FXK7XDO4ANS","short_pith_number":"pith:3SY7DGRF","schema_version":"1.0","canonical_sha256":"dcb1f19a25df77ab1fc5babf71bb806c8020c27b0e9749f0ef4d313a4724f4ed","source":{"kind":"arxiv","id":"2312.15197","version":1},"attestation_state":"computed","paper":{"title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aoxiong Yin, Changpeng Yang, Linjun Li, Minglei Li, Rongjie Huang, Tao Jin, Xinyu Duan, Xize Cheng, Zehan Wang, Zhou Zhao","submitted_at":"2023-12-23T08:45:57Z","abstract_excerpt":"Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delays and cascading errors associated with model cascading. However, talking head translation, converting audio-visual speech (i.e., talking head video) from one language into another, still confronts several challenges compared to audio speech: (1) Existing methods invariably rely on cascading, synthesizing via both audio and text, resulting in delays and cascading errors. (2) Talking head translation has a limited set "},"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":"2312.15197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-23T08:45:57Z","cross_cats_sorted":["cs.CL","cs.CV","eess.AS"],"title_canon_sha256":"1256413aa54dce782fce048e973115172ce04b274babd8686b1ab23f6a3570cf","abstract_canon_sha256":"941fc5b3cd4c15fa9319e21afb707c6192ccbebbd04842b14f6f6eaa1e61b06f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:32.176520Z","signature_b64":"gHEjoGUd5m7sl1jYo0ISCbCs2Z1zoNKpkKt6xH3sfBYiBM2OHx6oLqvlCmaDUu0tb4hUpJKLqdC0Ob1RNPTNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb1f19a25df77ab1fc5babf71bb806c8020c27b0e9749f0ef4d313a4724f4ed","last_reissued_at":"2026-07-05T07:27:32.176034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:32.176034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aoxiong Yin, Changpeng Yang, Linjun Li, Minglei Li, Rongjie Huang, Tao Jin, Xinyu Duan, Xize Cheng, Zehan Wang, Zhou Zhao","submitted_at":"2023-12-23T08:45:57Z","abstract_excerpt":"Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delays and cascading errors associated with model cascading. However, talking head translation, converting audio-visual speech (i.e., talking head video) from one language into another, still confronts several challenges compared to audio speech: (1) Existing methods invariably rely on cascading, synthesizing via both audio and text, resulting in delays and cascading errors. (2) Talking head translation has a limited set "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15197","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/2312.15197/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":"2312.15197","created_at":"2026-07-05T07:27:32.176093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15197v1","created_at":"2026-07-05T07:27:32.176093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15197","created_at":"2026-07-05T07:27:32.176093+00:00"},{"alias_kind":"pith_short_12","alias_value":"3SY7DGRF3532","created_at":"2026-07-05T07:27:32.176093+00:00"},{"alias_kind":"pith_short_16","alias_value":"3SY7DGRF3532WH6F","created_at":"2026-07-05T07:27:32.176093+00:00"},{"alias_kind":"pith_short_8","alias_value":"3SY7DGRF","created_at":"2026-07-05T07:27:32.176093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12723","citing_title":"Cross-Modal Watermarking for Authentic Audio Recovery and Tamper Localization in Synthesized Audiovisual Forgeries","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS","json":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS.json","graph_json":"https://pith.science/api/pith-number/3SY7DGRF3532WH6FXK7XDO4ANS/graph.json","events_json":"https://pith.science/api/pith-number/3SY7DGRF3532WH6FXK7XDO4ANS/events.json","paper":"https://pith.science/paper/3SY7DGRF"},"agent_actions":{"view_html":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS","download_json":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS.json","view_paper":"https://pith.science/paper/3SY7DGRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15197&json=true","fetch_graph":"https://pith.science/api/pith-number/3SY7DGRF3532WH6FXK7XDO4ANS/graph.json","fetch_events":"https://pith.science/api/pith-number/3SY7DGRF3532WH6FXK7XDO4ANS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS/action/storage_attestation","attest_author":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS/action/author_attestation","sign_citation":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS/action/citation_signature","submit_replication":"https://pith.science/pith/3SY7DGRF3532WH6FXK7XDO4ANS/action/replication_record"}},"created_at":"2026-07-05T07:27:32.176093+00:00","updated_at":"2026-07-05T07:27:32.176093+00:00"}