{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:66M3M5GMN474AVESYYFEDX7ZPD","short_pith_number":"pith:66M3M5GM","schema_version":"1.0","canonical_sha256":"f799b674cc6f3fc05492c60a41dff978da4b4a2aabe8e30a512d50aeaf94cf40","source":{"kind":"arxiv","id":"2305.13195","version":1},"attestation_state":"computed","paper":{"title":"U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bjoern W. Schuller, Jiangjian Xie, Xin Jing, Yi Chang, Zijiang Yang","submitted_at":"2023-05-22T16:25:19Z","abstract_excerpt":"Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability to produce high-quality synthesized neural speech in neural speech synthesis systems. In SGMs, the U-Net architecture and its variants have long dominated as the backbone since its first successful adoption. In this research, we mainly focus on the neural network in diffusion-model-based Text-to-Speech (TTS) systems and propose the U-DiT architecture, explori"},"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":"2305.13195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T16:25:19Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"48b609ad16a3caf8b75b2241655219f4d5c4c419f227e030fb78703d29f98ae0","abstract_canon_sha256":"2fe3b3aee2e3703b58ef1c3d862cffe623ecf980855717e6f57f48265bf5992a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:27.386088Z","signature_b64":"bQxJFWzkr9FuXqlomeLDUf3OcnFU4t//tr2+8mSXGaWRGVBgoE5EIhkj7OSYSF6Pr/jwHADtWo7J680D8AVnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f799b674cc6f3fc05492c60a41dff978da4b4a2aabe8e30a512d50aeaf94cf40","last_reissued_at":"2026-07-05T06:12:27.385617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:27.385617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bjoern W. Schuller, Jiangjian Xie, Xin Jing, Yi Chang, Zijiang Yang","submitted_at":"2023-05-22T16:25:19Z","abstract_excerpt":"Deep learning has led to considerable advances in text-to-speech synthesis. Most recently, the adoption of Score-based Generative Models (SGMs), also known as Diffusion Probabilistic Models (DPMs), has gained traction due to their ability to produce high-quality synthesized neural speech in neural speech synthesis systems. In SGMs, the U-Net architecture and its variants have long dominated as the backbone since its first successful adoption. In this research, we mainly focus on the neural network in diffusion-model-based Text-to-Speech (TTS) systems and propose the U-DiT architecture, explori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13195","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/2305.13195/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":"2305.13195","created_at":"2026-07-05T06:12:27.385688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13195v1","created_at":"2026-07-05T06:12:27.385688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13195","created_at":"2026-07-05T06:12:27.385688+00:00"},{"alias_kind":"pith_short_12","alias_value":"66M3M5GMN474","created_at":"2026-07-05T06:12:27.385688+00:00"},{"alias_kind":"pith_short_16","alias_value":"66M3M5GMN474AVES","created_at":"2026-07-05T06:12:27.385688+00:00"},{"alias_kind":"pith_short_8","alias_value":"66M3M5GM","created_at":"2026-07-05T06:12:27.385688+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/66M3M5GMN474AVESYYFEDX7ZPD","json":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD.json","graph_json":"https://pith.science/api/pith-number/66M3M5GMN474AVESYYFEDX7ZPD/graph.json","events_json":"https://pith.science/api/pith-number/66M3M5GMN474AVESYYFEDX7ZPD/events.json","paper":"https://pith.science/paper/66M3M5GM"},"agent_actions":{"view_html":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD","download_json":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD.json","view_paper":"https://pith.science/paper/66M3M5GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13195&json=true","fetch_graph":"https://pith.science/api/pith-number/66M3M5GMN474AVESYYFEDX7ZPD/graph.json","fetch_events":"https://pith.science/api/pith-number/66M3M5GMN474AVESYYFEDX7ZPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD/action/storage_attestation","attest_author":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD/action/author_attestation","sign_citation":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD/action/citation_signature","submit_replication":"https://pith.science/pith/66M3M5GMN474AVESYYFEDX7ZPD/action/replication_record"}},"created_at":"2026-07-05T06:12:27.385688+00:00","updated_at":"2026-07-05T06:12:27.385688+00:00"}