{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QDG5SBON3GCSKBHGI4BT5DF5RE","short_pith_number":"pith:QDG5SBON","schema_version":"1.0","canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","source":{"kind":"arxiv","id":"2608.12951","version":1},"attestation_state":"computed","paper":{"title":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Changhao Pan, Fei Wu, Wenxiang Guo, Zhou Zhao, Ziyue Jiang","submitted_at":"2026-08-13T08:27:22Z","abstract_excerpt":"Vocalized audio synthesis, the task of generating audio in which intelligible speech is embedded within an environmental soundscape, underpins applications such as podcast production and video dubbing. Existing Text-to-Audio (T2A) systems either reduce quoted speech to unintelligible vocal murmur or delegate it to a separate TTS model with post-hoc mixing, which forfeits control over when speech occurs and how it interacts with the scene. We present VoxAudio, a causal autoregressive flow matching model that addresses this problem from three complementary aspects. At the architecture level, chu"},"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":"2608.12951","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-13T08:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"ce4d0856796317bf7f0a54a4449948a414ca858ad5f778ebe71546c6ca2316fe","abstract_canon_sha256":"e07ddf70c8d1625b175cb06470ed4678f27e906f9996c8c256adfdcf12d3fcf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:59:34.340077Z","signature_b64":"5WEv0o1qAxFSxJjmY3J/e68yNrbfz9X/EOYPNAo+bq+s86rfYmZZnUjaqHQTLVqFAT5jE3DSAiWhoCV89fe6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80cdd905cdd9852504e647033e8cbd89287dbb68d301554e00a2c867fe617aaa","last_reissued_at":"2026-08-14T00:59:34.327908Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:59:34.327908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxAudio: Vocalized Audio Synthesis via Multi-Reward Autoregressive Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Changhao Pan, Fei Wu, Wenxiang Guo, Zhou Zhao, Ziyue Jiang","submitted_at":"2026-08-13T08:27:22Z","abstract_excerpt":"Vocalized audio synthesis, the task of generating audio in which intelligible speech is embedded within an environmental soundscape, underpins applications such as podcast production and video dubbing. Existing Text-to-Audio (T2A) systems either reduce quoted speech to unintelligible vocal murmur or delegate it to a separate TTS model with post-hoc mixing, which forfeits control over when speech occurs and how it interacts with the scene. We present VoxAudio, a causal autoregressive flow matching model that addresses this problem from three complementary aspects. At the architecture level, chu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12951","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/2608.12951/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":"2608.12951","created_at":"2026-08-14T00:59:34.337541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12951v1","created_at":"2026-08-14T00:59:34.337541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12951","created_at":"2026-08-14T00:59:34.337541+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDG5SBON3GCS","created_at":"2026-08-14T00:59:34.337541+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDG5SBON3GCSKBHG","created_at":"2026-08-14T00:59:34.337541+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDG5SBON","created_at":"2026-08-14T00:59:34.337541+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/QDG5SBON3GCSKBHGI4BT5DF5RE","json":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE.json","graph_json":"https://pith.science/api/pith-number/QDG5SBON3GCSKBHGI4BT5DF5RE/graph.json","events_json":"https://pith.science/api/pith-number/QDG5SBON3GCSKBHGI4BT5DF5RE/events.json","paper":"https://pith.science/paper/QDG5SBON"},"agent_actions":{"view_html":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE","download_json":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE.json","view_paper":"https://pith.science/paper/QDG5SBON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12951&json=true","fetch_graph":"https://pith.science/api/pith-number/QDG5SBON3GCSKBHGI4BT5DF5RE/graph.json","fetch_events":"https://pith.science/api/pith-number/QDG5SBON3GCSKBHGI4BT5DF5RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/action/storage_attestation","attest_author":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/action/author_attestation","sign_citation":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/action/citation_signature","submit_replication":"https://pith.science/pith/QDG5SBON3GCSKBHGI4BT5DF5RE/action/replication_record"}},"created_at":"2026-08-14T00:59:34.337541+00:00","updated_at":"2026-08-14T00:59:34.337541+00:00"}