{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PDTB4YC535A5EUGZMDW4VTAXFX","short_pith_number":"pith:PDTB4YC5","schema_version":"1.0","canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","source":{"kind":"arxiv","id":"2301.13662","version":2},"attestation_state":"computed","paper":{"title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Dongchao Yang, Helen Meng, Rongjie Huang, Songxiang Liu","submitted_at":"2023-01-31T14:26:52Z","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"},"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":"2301.13662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7","abstract_canon_sha256":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:27.762669Z","signature_b64":"CiR/VT42y4Dr3TES6eyHKrVhRG+J6yFFbmmXibAy1K+TyR2Q8km/a9QIFiXj59qMnrx6OC13YuaXlzZSdz6ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","last_reissued_at":"2026-07-05T06:24:27.762266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:27.762266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Dongchao Yang, Helen Meng, Rongjie Huang, Songxiang Liu","submitted_at":"2023-01-31T14:26:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13662","kind":"arxiv","version":2},"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/2301.13662/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":"2301.13662","created_at":"2026-07-05T06:24:27.762323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13662v2","created_at":"2026-07-05T06:24:27.762323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13662","created_at":"2026-07-05T06:24:27.762323+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDTB4YC535A5","created_at":"2026-07-05T06:24:27.762323+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDTB4YC535A5EUGZ","created_at":"2026-07-05T06:24:27.762323+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDTB4YC5","created_at":"2026-07-05T06:24:27.762323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08363","citing_title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX","json":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX.json","graph_json":"https://pith.science/api/pith-number/PDTB4YC535A5EUGZMDW4VTAXFX/graph.json","events_json":"https://pith.science/api/pith-number/PDTB4YC535A5EUGZMDW4VTAXFX/events.json","paper":"https://pith.science/paper/PDTB4YC5"},"agent_actions":{"view_html":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX","download_json":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX.json","view_paper":"https://pith.science/paper/PDTB4YC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13662&json=true","fetch_graph":"https://pith.science/api/pith-number/PDTB4YC535A5EUGZMDW4VTAXFX/graph.json","fetch_events":"https://pith.science/api/pith-number/PDTB4YC535A5EUGZMDW4VTAXFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/action/storage_attestation","attest_author":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/action/author_attestation","sign_citation":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/action/citation_signature","submit_replication":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/action/replication_record"}},"created_at":"2026-07-05T06:24:27.762323+00:00","updated_at":"2026-07-05T06:24:27.762323+00:00"}