{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GWWEXII44LVCEDGW7EKH35ZSW2","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":"67ff5f873afb0ba452cf1f84b48162eca2da23a4ba8428207831f34283618c25","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-22T04:37:41Z","title_canon_sha256":"018e63e0e9a37f4a250f963582ec0a8facd2366b6f03ec9ec4d240ef8ef6d9d7"},"schema_version":"1.0","source":{"id":"2305.12708","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12708","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12708v2","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12708","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"GWWEXII44LVC","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_16","alias_value":"GWWEXII44LVCEDGW","created_at":"2026-07-05T08:10:14Z"},{"alias_kind":"pith_short_8","alias_value":"GWWEXII4","created_at":"2026-07-05T08:10:14Z"}],"graph_snapshots":[{"event_id":"sha256:714e9bd500dec9bb5bf1a460ac143989aab2e2f03ebbe9411b14c6ca2db476a5","target":"graph","created_at":"2026-07-05T08:10:14Z","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/2305.12708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch, rhythm, and energy, but also on the physical environment. In this work, we propose ViT-TTS, the first visual TTS model with scalable diffusion transformers. ViT-TTS complement the phoneme sequence with the visual information to generate high-perceived audio, opening up new avenues for practical applications of AR and VR to allow a more immersive and realistic ","authors_text":"Hong Chen, Huadai Liu, Jinzheng He, Maozong Zheng, Rongjie Huang, Wenqiang Xu, Xuan Lin, Zhou Zhao","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-22T04:37:41Z","title":"ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12708","kind":"arxiv","version":2},"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":"sha256:23e1f9fbf107eb9f994bbd52bf25443810ca8d2f908fb61ad48e2393d90cc3bc","target":"record","created_at":"2026-07-05T08:10:14Z","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":"67ff5f873afb0ba452cf1f84b48162eca2da23a4ba8428207831f34283618c25","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-22T04:37:41Z","title_canon_sha256":"018e63e0e9a37f4a250f963582ec0a8facd2366b6f03ec9ec4d240ef8ef6d9d7"},"schema_version":"1.0","source":{"id":"2305.12708","kind":"arxiv","version":2}},"canonical_sha256":"35ac4ba11ce2ea220cd6f9147df732b69cb20cb81492c4fdf818bf2307b6a304","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35ac4ba11ce2ea220cd6f9147df732b69cb20cb81492c4fdf818bf2307b6a304","first_computed_at":"2026-07-05T08:10:14.033161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:14.033161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NHygY8JHKvyzyXwFO5I1wsd46ahv73B5PnzmFDxWcMHUrcSN9ZFz5IOgQHCsq1jggd0rkPDeyTjBl9iYViEIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:14.033631Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12708","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23e1f9fbf107eb9f994bbd52bf25443810ca8d2f908fb61ad48e2393d90cc3bc","sha256:714e9bd500dec9bb5bf1a460ac143989aab2e2f03ebbe9411b14c6ca2db476a5"],"state_sha256":"2773d3f04c6d29c3b9ba6de3f298ced90500d458948b09f2f11a33e190ad8947"}