{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:66M3M5GMN474AVESYYFEDX7ZPD","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":"2fe3b3aee2e3703b58ef1c3d862cffe623ecf980855717e6f57f48265bf5992a","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T16:25:19Z","title_canon_sha256":"48b609ad16a3caf8b75b2241655219f4d5c4c419f227e030fb78703d29f98ae0"},"schema_version":"1.0","source":{"id":"2305.13195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13195","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13195v1","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13195","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_12","alias_value":"66M3M5GMN474","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_16","alias_value":"66M3M5GMN474AVES","created_at":"2026-07-05T06:12:27Z"},{"alias_kind":"pith_short_8","alias_value":"66M3M5GM","created_at":"2026-07-05T06:12:27Z"}],"graph_snapshots":[{"event_id":"sha256:6b6d2d9798e8d91962c9dd84aeb71fc02244326d332acf7e4852f1a768f2ea49","target":"graph","created_at":"2026-07-05T06:12:27Z","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/2305.13195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andreas Triantafyllopoulos, Bjoern W. Schuller, Jiangjian Xie, Xin Jing, Yi Chang, Zijiang Yang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T16:25:19Z","title":"U-DiT TTS: U-Diffusion Vision Transformer for Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13195","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:bad4ab661a2529a6367403f6066ff22587d39cb41e0837e2ba4152ec48ef6ddb","target":"record","created_at":"2026-07-05T06:12:27Z","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":"2fe3b3aee2e3703b58ef1c3d862cffe623ecf980855717e6f57f48265bf5992a","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T16:25:19Z","title_canon_sha256":"48b609ad16a3caf8b75b2241655219f4d5c4c419f227e030fb78703d29f98ae0"},"schema_version":"1.0","source":{"id":"2305.13195","kind":"arxiv","version":1}},"canonical_sha256":"f799b674cc6f3fc05492c60a41dff978da4b4a2aabe8e30a512d50aeaf94cf40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f799b674cc6f3fc05492c60a41dff978da4b4a2aabe8e30a512d50aeaf94cf40","first_computed_at":"2026-07-05T06:12:27.385617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:27.385617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQxJFWzkr9FuXqlomeLDUf3OcnFU4t//tr2+8mSXGaWRGVBgoE5EIhkj7OSYSF6Pr/jwHADtWo7J680D8AVnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:27.386088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bad4ab661a2529a6367403f6066ff22587d39cb41e0837e2ba4152ec48ef6ddb","sha256:6b6d2d9798e8d91962c9dd84aeb71fc02244326d332acf7e4852f1a768f2ea49"],"state_sha256":"fbc82fb2dab1b744e22811ea2d67552ace441b9c5f5e3154dc0aa9e4929bbef7"}