{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HRQ2DNVQ724XG7D74O4VHRIIHZ","short_pith_number":"pith:HRQ2DNVQ","schema_version":"1.0","canonical_sha256":"3c61a1b6b0feb9737c7fe3b953c5083e484e9a830de8fa25eed53549e3812a87","source":{"kind":"arxiv","id":"2504.02433","version":2},"attestation_state":"computed","paper":{"title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Chaonan Ji, Guangyuan Wang, Jinwei Qi, Liefeng Bo, Peng Zhang, Sheng Xu, Zhongjian Wang","submitted_at":"2025-04-03T09:48:13Z","abstract_excerpt":"Although significant progress has been made in audio-driven talking head generation, text-driven methods remain underexplored. In this work, we present OmniTalker, a unified framework that jointly generates synchronized talking audio-video content from input text while emulating the speaking and facial movement styles of the target identity, including speech characteristics, head motion, and facial dynamics. Our framework adopts a dual-branch diffusion transformer (DiT) architecture, with one branch dedicated to audio generation and the other to video synthesis. At the shallow layers, cross-mo"},"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":"2504.02433","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T09:48:13Z","cross_cats_sorted":[],"title_canon_sha256":"9260f54e352eea1213af124fb7eff4cc78119b09af3e07409d1009bf4d265160","abstract_canon_sha256":"cc155e7fc949f5337c2154af90ad6886b2c2dea3971f2359caaa3101489c8042"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:57.610096Z","signature_b64":"xxKs1Ph2JlSRYT6HSOlJF4SfWHWYdGbYr9shwz8+uFNXO0FNdIzudt9v21e5yXy12bMjIGCv8kRcYjG5jSo9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c61a1b6b0feb9737c7fe3b953c5083e484e9a830de8fa25eed53549e3812a87","last_reissued_at":"2026-07-05T11:14:57.609610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:57.609610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style Mimicking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Chaonan Ji, Guangyuan Wang, Jinwei Qi, Liefeng Bo, Peng Zhang, Sheng Xu, Zhongjian Wang","submitted_at":"2025-04-03T09:48:13Z","abstract_excerpt":"Although significant progress has been made in audio-driven talking head generation, text-driven methods remain underexplored. In this work, we present OmniTalker, a unified framework that jointly generates synchronized talking audio-video content from input text while emulating the speaking and facial movement styles of the target identity, including speech characteristics, head motion, and facial dynamics. Our framework adopts a dual-branch diffusion transformer (DiT) architecture, with one branch dedicated to audio generation and the other to video synthesis. At the shallow layers, cross-mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02433","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/2504.02433/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":"2504.02433","created_at":"2026-07-05T11:14:57.609670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02433v2","created_at":"2026-07-05T11:14:57.609670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02433","created_at":"2026-07-05T11:14:57.609670+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRQ2DNVQ724X","created_at":"2026-07-05T11:14:57.609670+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRQ2DNVQ724XG7D7","created_at":"2026-07-05T11:14:57.609670+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRQ2DNVQ","created_at":"2026-07-05T11:14:57.609670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01157","citing_title":"InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ","json":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ.json","graph_json":"https://pith.science/api/pith-number/HRQ2DNVQ724XG7D74O4VHRIIHZ/graph.json","events_json":"https://pith.science/api/pith-number/HRQ2DNVQ724XG7D74O4VHRIIHZ/events.json","paper":"https://pith.science/paper/HRQ2DNVQ"},"agent_actions":{"view_html":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ","download_json":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ.json","view_paper":"https://pith.science/paper/HRQ2DNVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02433&json=true","fetch_graph":"https://pith.science/api/pith-number/HRQ2DNVQ724XG7D74O4VHRIIHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HRQ2DNVQ724XG7D74O4VHRIIHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ/action/storage_attestation","attest_author":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ/action/author_attestation","sign_citation":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ/action/citation_signature","submit_replication":"https://pith.science/pith/HRQ2DNVQ724XG7D74O4VHRIIHZ/action/replication_record"}},"created_at":"2026-07-05T11:14:57.609670+00:00","updated_at":"2026-07-05T11:14:57.609670+00:00"}