{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRUIKRIVSLB2NBAVHCCULKCH55","short_pith_number":"pith:BRUIKRIV","schema_version":"1.0","canonical_sha256":"0c6885451592c3a68415388545a847ef509ce7da1fddb0893088f84706406fc1","source":{"kind":"arxiv","id":"2412.19259","version":1},"attestation_state":"computed","paper":{"title":"VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chaeyoung Jung, Jaemin Jung, Joon Son Chung, Junseok Ahn, Tan Dat Nguyen, Youngjoon Jang","submitted_at":"2024-12-26T15:52:58Z","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"},"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":"2412.19259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-12-26T15:52:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d608efe77680a7bbb1d47f89755d677471a3525c551f06468d3c3e1aa05bd21b","abstract_canon_sha256":"ad7f8e045d96dffea686cba72579dd51c6bb8dfa6f62b91cd577fe024e44c288"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:33.008774Z","signature_b64":"Jn4ICj+3IgL4wYn47/FMX62LFzIHN6j6DRD2E/mY28OHoIz0uibsWWW2aOvWPtHAlS9WKvdpSLWm0ht6+B5kDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c6885451592c3a68415388545a847ef509ce7da1fddb0893088f84706406fc1","last_reissued_at":"2026-07-05T09:54:33.008360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:33.008360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chaeyoung Jung, Jaemin Jung, Joon Son Chung, Junseok Ahn, Tan Dat Nguyen, Youngjoon Jang","submitted_at":"2024-12-26T15:52:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19259","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/2412.19259/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":"2412.19259","created_at":"2026-07-05T09:54:33.008426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19259v1","created_at":"2026-07-05T09:54:33.008426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19259","created_at":"2026-07-05T09:54:33.008426+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRUIKRIVSLB2","created_at":"2026-07-05T09:54:33.008426+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRUIKRIVSLB2NBAV","created_at":"2026-07-05T09:54:33.008426+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRUIKRIV","created_at":"2026-07-05T09:54:33.008426+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/BRUIKRIVSLB2NBAVHCCULKCH55","json":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55.json","graph_json":"https://pith.science/api/pith-number/BRUIKRIVSLB2NBAVHCCULKCH55/graph.json","events_json":"https://pith.science/api/pith-number/BRUIKRIVSLB2NBAVHCCULKCH55/events.json","paper":"https://pith.science/paper/BRUIKRIV"},"agent_actions":{"view_html":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55","download_json":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55.json","view_paper":"https://pith.science/paper/BRUIKRIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19259&json=true","fetch_graph":"https://pith.science/api/pith-number/BRUIKRIVSLB2NBAVHCCULKCH55/graph.json","fetch_events":"https://pith.science/api/pith-number/BRUIKRIVSLB2NBAVHCCULKCH55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55/action/storage_attestation","attest_author":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55/action/author_attestation","sign_citation":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55/action/citation_signature","submit_replication":"https://pith.science/pith/BRUIKRIVSLB2NBAVHCCULKCH55/action/replication_record"}},"created_at":"2026-07-05T09:54:33.008426+00:00","updated_at":"2026-07-05T09:54:33.008426+00:00"}