{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IRTRKRY2N3YOSHTNZV5Y3DGV4X","short_pith_number":"pith:IRTRKRY2","schema_version":"1.0","canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","source":{"kind":"arxiv","id":"2503.22265","version":1},"attestation_state":"computed","paper":{"title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chang Liu, Chaofan Ding, Haomin Zhang, Junjie Zheng, Xinhan Di, Zihao Chen","submitted_at":"2025-03-28T09:29:08Z","abstract_excerpt":"Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and audio-visual synchronization are effectively achieved. However, in real-world scenarios, speech and audio often coexist in videos simultaneously, and the end-to-end generation of synchronous speech and audio given video and text conditions are not well studied. Therefore, we propose an end-to-end multi-modal generation framework that simultaneously produces spe"},"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":"2503.22265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T09:29:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"b971c79527b40a52f787b12d94b9371449f184476a9505e8650be45b40158a10","abstract_canon_sha256":"b132ca1e372f5d0d65b0cb22c3dc55e6b530c3c15668acf900d4c8ce164ff3e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:51.144757Z","signature_b64":"1EUJ33xizY5kfBXGkztSdM9bEawcBbNOBr/8dWim3BdSllRPW+RaxT6y7FePb7w2GyRnL8kv/vylH2ihKIBBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446715471a6ef0e91e6dcd7b8d8cd5e5fe0ebd18a92f0d80495ac49f1e3703ed","last_reissued_at":"2026-07-05T10:40:51.144264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:51.144264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chang Liu, Chaofan Ding, Haomin Zhang, Junjie Zheng, Xinhan Di, Zihao Chen","submitted_at":"2025-03-28T09:29:08Z","abstract_excerpt":"Currently, high-quality, synchronized audio is synthesized using various multi-modal joint learning frameworks, leveraging video and optional text inputs. In the video-to-audio benchmarks, video-to-audio quality, semantic alignment, and audio-visual synchronization are effectively achieved. However, in real-world scenarios, speech and audio often coexist in videos simultaneously, and the end-to-end generation of synchronous speech and audio given video and text conditions are not well studied. Therefore, we propose an end-to-end multi-modal generation framework that simultaneously produces spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22265","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/2503.22265/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":"2503.22265","created_at":"2026-07-05T10:40:51.144323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22265v1","created_at":"2026-07-05T10:40:51.144323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22265","created_at":"2026-07-05T10:40:51.144323+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRTRKRY2N3YO","created_at":"2026-07-05T10:40:51.144323+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRTRKRY2N3YOSHTN","created_at":"2026-07-05T10:40:51.144323+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRTRKRY2","created_at":"2026-07-05T10:40:51.144323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09098","citing_title":"HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01284","citing_title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X","json":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X.json","graph_json":"https://pith.science/api/pith-number/IRTRKRY2N3YOSHTNZV5Y3DGV4X/graph.json","events_json":"https://pith.science/api/pith-number/IRTRKRY2N3YOSHTNZV5Y3DGV4X/events.json","paper":"https://pith.science/paper/IRTRKRY2"},"agent_actions":{"view_html":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X","download_json":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X.json","view_paper":"https://pith.science/paper/IRTRKRY2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22265&json=true","fetch_graph":"https://pith.science/api/pith-number/IRTRKRY2N3YOSHTNZV5Y3DGV4X/graph.json","fetch_events":"https://pith.science/api/pith-number/IRTRKRY2N3YOSHTNZV5Y3DGV4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/action/storage_attestation","attest_author":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/action/author_attestation","sign_citation":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/action/citation_signature","submit_replication":"https://pith.science/pith/IRTRKRY2N3YOSHTNZV5Y3DGV4X/action/replication_record"}},"created_at":"2026-07-05T10:40:51.144323+00:00","updated_at":"2026-07-05T10:40:51.144323+00:00"}