{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G5N4D7NAEPBCDUCYZU7RIGQYGV","short_pith_number":"pith:G5N4D7NA","schema_version":"1.0","canonical_sha256":"375bc1fda023c221d058cd3f141a18356a6f0cdbd1ae956cafbee9f2341e9199","source":{"kind":"arxiv","id":"2211.12171","version":1},"attestation_state":"computed","paper":{"title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Sheng Zhao, Xu Tan, Yichong Leng, Yihan Wu, Zhifang Guo","submitted_at":"2022-11-22T10:58:38Z","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"},"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":"2211.12171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-22T10:58:38Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"53808b4e2d0db75e711058ac0fd01c0c8f48b5967d14e953b4a8ec4d79e1c653","abstract_canon_sha256":"78af52f7939a45346fa5b67b93f0349f31948810d7b1d16bd21c388a7454ea1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:14.009296Z","signature_b64":"wpsTBPsRCc0iHojCvYf2Vj59j37Zeepz+DNNLAjdic42gEbJHl+oGWAmQHRi7KLn/uf0XZ9Pc5dZYCAAIIUXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375bc1fda023c221d058cd3f141a18356a6f0cdbd1ae956cafbee9f2341e9199","last_reissued_at":"2026-07-05T05:18:14.008861Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:14.008861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Sheng Zhao, Xu Tan, Yichong Leng, Yihan Wu, Zhifang Guo","submitted_at":"2022-11-22T10:58:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12171","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/2211.12171/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":"2211.12171","created_at":"2026-07-05T05:18:14.008920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12171v1","created_at":"2026-07-05T05:18:14.008920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12171","created_at":"2026-07-05T05:18:14.008920+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5N4D7NAEPBC","created_at":"2026-07-05T05:18:14.008920+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5N4D7NAEPBCDUCY","created_at":"2026-07-05T05:18:14.008920+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5N4D7NA","created_at":"2026-07-05T05:18:14.008920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08363","citing_title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV","json":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV.json","graph_json":"https://pith.science/api/pith-number/G5N4D7NAEPBCDUCYZU7RIGQYGV/graph.json","events_json":"https://pith.science/api/pith-number/G5N4D7NAEPBCDUCYZU7RIGQYGV/events.json","paper":"https://pith.science/paper/G5N4D7NA"},"agent_actions":{"view_html":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV","download_json":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV.json","view_paper":"https://pith.science/paper/G5N4D7NA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12171&json=true","fetch_graph":"https://pith.science/api/pith-number/G5N4D7NAEPBCDUCYZU7RIGQYGV/graph.json","fetch_events":"https://pith.science/api/pith-number/G5N4D7NAEPBCDUCYZU7RIGQYGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV/action/storage_attestation","attest_author":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV/action/author_attestation","sign_citation":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV/action/citation_signature","submit_replication":"https://pith.science/pith/G5N4D7NAEPBCDUCYZU7RIGQYGV/action/replication_record"}},"created_at":"2026-07-05T05:18:14.008920+00:00","updated_at":"2026-07-05T05:18:14.008920+00:00"}