{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PNTJRUHLUB346MOLZ6UOOCMANA","short_pith_number":"pith:PNTJRUHL","schema_version":"1.0","canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","source":{"kind":"arxiv","id":"2508.00733","version":4},"attestation_state":"computed","paper":{"title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Chunyu Qiang, Di Zhang, Feng Deng, Jun Wang, Kun Gai, Le Wang","submitted_at":"2025-08-01T16:03:57Z","abstract_excerpt":"We present AudioGen-Omni - a unified approach based on multimodal diffusion transformers (MMDit), capable of generating high-fidelity audio, speech, and song coherently synchronized with the input video. AudioGen-Omni introduces a novel joint training paradigm that seamlessly integrates large-scale video-text-audio corpora, enabling a model capable of generating semantically rich, acoustically diverse audio conditioned on multimodal inputs and adaptable to a wide range of audio generation tasks. AudioGen-Omni employs a unified lyrics-transcription encoder that encodes graphemes and phonemes fr"},"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":"2508.00733","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-08-01T16:03:57Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"77bdfb1ece849d55ea090597688274474dcc02dabbcee9b6f57135c90682eaea","abstract_canon_sha256":"397edfa632cf18268c208e2f30af9da85562b20e7cb63ba1a843a93826819083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:58.835275Z","signature_b64":"xAAsHhrQ/SN3CSlHGsi6BE8JN2QMzIGi+ibMgDSJXmubZFK5/C2Xmxj7u4/bTGHm6zQMVnosQxcwiJYf2luIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b6698d0eba077cf31cbcfa8e70980682016e7db1a5b0c39cbee7c6f78e71071","last_reissued_at":"2026-07-05T11:49:58.834833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:58.834833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chen Zhang, Chunyu Qiang, Di Zhang, Feng Deng, Jun Wang, Kun Gai, Le Wang","submitted_at":"2025-08-01T16:03:57Z","abstract_excerpt":"We present AudioGen-Omni - a unified approach based on multimodal diffusion transformers (MMDit), capable of generating high-fidelity audio, speech, and song coherently synchronized with the input video. AudioGen-Omni introduces a novel joint training paradigm that seamlessly integrates large-scale video-text-audio corpora, enabling a model capable of generating semantically rich, acoustically diverse audio conditioned on multimodal inputs and adaptable to a wide range of audio generation tasks. AudioGen-Omni employs a unified lyrics-transcription encoder that encodes graphemes and phonemes fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00733","kind":"arxiv","version":4},"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/2508.00733/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":"2508.00733","created_at":"2026-07-05T11:49:58.834890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00733v4","created_at":"2026-07-05T11:49:58.834890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00733","created_at":"2026-07-05T11:49:58.834890+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNTJRUHLUB34","created_at":"2026-07-05T11:49:58.834890+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNTJRUHLUB346MOL","created_at":"2026-07-05T11:49:58.834890+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNTJRUHL","created_at":"2026-07-05T11:49:58.834890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30940","citing_title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02731","citing_title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10542","citing_title":"VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15086","citing_title":"ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA","json":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA.json","graph_json":"https://pith.science/api/pith-number/PNTJRUHLUB346MOLZ6UOOCMANA/graph.json","events_json":"https://pith.science/api/pith-number/PNTJRUHLUB346MOLZ6UOOCMANA/events.json","paper":"https://pith.science/paper/PNTJRUHL"},"agent_actions":{"view_html":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA","download_json":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA.json","view_paper":"https://pith.science/paper/PNTJRUHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00733&json=true","fetch_graph":"https://pith.science/api/pith-number/PNTJRUHLUB346MOLZ6UOOCMANA/graph.json","fetch_events":"https://pith.science/api/pith-number/PNTJRUHLUB346MOLZ6UOOCMANA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/action/storage_attestation","attest_author":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/action/author_attestation","sign_citation":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/action/citation_signature","submit_replication":"https://pith.science/pith/PNTJRUHLUB346MOLZ6UOOCMANA/action/replication_record"}},"created_at":"2026-07-05T11:49:58.834890+00:00","updated_at":"2026-07-05T11:49:58.834890+00:00"}