{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PDTB4YC535A5EUGZMDW4VTAXFX","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":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7"},"schema_version":"1.0","source":{"id":"2301.13662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13662","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13662v2","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13662","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"PDTB4YC535A5","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"PDTB4YC535A5EUGZ","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"PDTB4YC5","created_at":"2026-07-05T06:24:27Z"}],"graph_snapshots":[{"event_id":"sha256:3dea26f2dc5903498cc16f4093f8cfb23652b6c3dc193bacc822334e08beea70","target":"graph","created_at":"2026-07-05T06:24:27Z","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/2301.13662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using categorical index to denote different speaking style. However, there are limitations in the diversity of expressiveness, as these models can only generate the pre-defined styles. (2) Using reference speech as style input, which results in a problem that the extracted style information is not intuitive or interpretable. In this study, we attempt to use natural language","authors_text":"Chao Weng, Dongchao Yang, Helen Meng, Rongjie Huang, Songxiang Liu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13662","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":"sha256:627e0fac1c10673c2872e6dd04ec853da7caecfb0417e0e6434e45ddb0073734","target":"record","created_at":"2026-07-05T06:24:27Z","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":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7"},"schema_version":"1.0","source":{"id":"2301.13662","kind":"arxiv","version":2}},"canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","first_computed_at":"2026-07-05T06:24:27.762266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:27.762266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CiR/VT42y4Dr3TES6eyHKrVhRG+J6yFFbmmXibAy1K+TyR2Q8km/a9QIFiXj59qMnrx6OC13YuaXlzZSdz6ZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:27.762669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:627e0fac1c10673c2872e6dd04ec853da7caecfb0417e0e6434e45ddb0073734","sha256:3dea26f2dc5903498cc16f4093f8cfb23652b6c3dc193bacc822334e08beea70"],"state_sha256":"1bcec779940f15f0ebbffbac7f5a006c603ed668e7c73a2cca2c89271b4f218e"}