{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G5N4D7NAEPBCDUCYZU7RIGQYGV","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":"78af52f7939a45346fa5b67b93f0349f31948810d7b1d16bd21c388a7454ea1e","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-22T10:58:38Z","title_canon_sha256":"53808b4e2d0db75e711058ac0fd01c0c8f48b5967d14e953b4a8ec4d79e1c653"},"schema_version":"1.0","source":{"id":"2211.12171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.12171","created_at":"2026-07-05T05:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"2211.12171v1","created_at":"2026-07-05T05:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12171","created_at":"2026-07-05T05:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"G5N4D7NAEPBC","created_at":"2026-07-05T05:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"G5N4D7NAEPBCDUCY","created_at":"2026-07-05T05:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"G5N4D7NA","created_at":"2026-07-05T05:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:b2b4074e5948ddc21c189780770fb753b39e5bae3157e66abb719b4e3c382f57","target":"graph","created_at":"2026-07-05T05:18:14Z","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/2211.12171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using a text description as prompt to guide the generation of text or images (e.g., GPT-3 or DALLE-2) has drawn wide attention recently. Beyond text and image generation, in this work, we explore the possibility of utilizing text descriptions to guide speech synthesis. Thus, we develop a text-to-speech (TTS) system (dubbed as PromptTTS) that takes a prompt with both style and content descriptions as input to synthesize the corresponding speech. Specifically, PromptTTS consists of a style encoder and a content encoder to extract the corresponding representations from the prompt, and a speech de","authors_text":"Sheng Zhao, Xu Tan, Yichong Leng, Yihan Wu, Zhifang Guo","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-22T10:58:38Z","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12171","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":"sha256:93382e81b0f443c831fc333f950eeedc2ab0171711657b81686fa4c8d950d919","target":"record","created_at":"2026-07-05T05:18:14Z","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":"78af52f7939a45346fa5b67b93f0349f31948810d7b1d16bd21c388a7454ea1e","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-22T10:58:38Z","title_canon_sha256":"53808b4e2d0db75e711058ac0fd01c0c8f48b5967d14e953b4a8ec4d79e1c653"},"schema_version":"1.0","source":{"id":"2211.12171","kind":"arxiv","version":1}},"canonical_sha256":"375bc1fda023c221d058cd3f141a18356a6f0cdbd1ae956cafbee9f2341e9199","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"375bc1fda023c221d058cd3f141a18356a6f0cdbd1ae956cafbee9f2341e9199","first_computed_at":"2026-07-05T05:18:14.008861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:14.008861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wpsTBPsRCc0iHojCvYf2Vj59j37Zeepz+DNNLAjdic42gEbJHl+oGWAmQHRi7KLn/uf0XZ9Pc5dZYCAAIIUXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:14.009296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.12171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93382e81b0f443c831fc333f950eeedc2ab0171711657b81686fa4c8d950d919","sha256:b2b4074e5948ddc21c189780770fb753b39e5bae3157e66abb719b4e3c382f57"],"state_sha256":"e5ad00f7dc8cd0d55fc61eb63958ef3d4b5d46da32e32c8b1d26b3468536cc34"}