{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BRUIKRIVSLB2NBAVHCCULKCH55","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ad7f8e045d96dffea686cba72579dd51c6bb8dfa6f62b91cd577fe024e44c288","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T15:52:58Z","title_canon_sha256":"d608efe77680a7bbb1d47f89755d677471a3525c551f06468d3c3e1aa05bd21b"},"schema_version":"1.0","source":{"id":"2412.19259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19259","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19259v1","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19259","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"BRUIKRIVSLB2","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"BRUIKRIVSLB2NBAV","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"BRUIKRIV","created_at":"2026-07-05T09:54:33Z"}],"graph_snapshots":[{"event_id":"sha256:fa03572a5436deeda97971a472a171d5b83d0e8a7e4e15972cf16103fab7894d","target":"graph","created_at":"2026-07-05T09:54:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.19259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy conditions remains a significant and underexplored challenge in the field. To address this, we present a novel audio generation pipeline named VoiceDiT. This pipeline includes three key components: (1) the creation of a large-scale synthetic speech dataset for pre-training and a refined real-world speech dataset for fine-tuning, (2) the Dual-DiT, a model designed t","authors_text":"Chaeyoung Jung, Jaemin Jung, Joon Son Chung, Junseok Ahn, Tan Dat Nguyen, Youngjoon Jang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T15:52:58Z","title":"VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19259","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3f5360c1bd0536c8e93844454af0c67f113ff2469829332880cd6bcdfa1a797","target":"record","created_at":"2026-07-05T09:54:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ad7f8e045d96dffea686cba72579dd51c6bb8dfa6f62b91cd577fe024e44c288","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T15:52:58Z","title_canon_sha256":"d608efe77680a7bbb1d47f89755d677471a3525c551f06468d3c3e1aa05bd21b"},"schema_version":"1.0","source":{"id":"2412.19259","kind":"arxiv","version":1}},"canonical_sha256":"0c6885451592c3a68415388545a847ef509ce7da1fddb0893088f84706406fc1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c6885451592c3a68415388545a847ef509ce7da1fddb0893088f84706406fc1","first_computed_at":"2026-07-05T09:54:33.008360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:33.008360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jn4ICj+3IgL4wYn47/FMX62LFzIHN6j6DRD2E/mY28OHoIz0uibsWWW2aOvWPtHAlS9WKvdpSLWm0ht6+B5kDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:33.008774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3f5360c1bd0536c8e93844454af0c67f113ff2469829332880cd6bcdfa1a797","sha256:fa03572a5436deeda97971a472a171d5b83d0e8a7e4e15972cf16103fab7894d"],"state_sha256":"1b4b0035c53f2ae12ffdda80a7e63b3ddca289d270416c9d27442aa80f6da1bf"}