{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AJ34KW2E27CF3XCUFZIFTE27VA","short_pith_number":"pith:AJ34KW2E","schema_version":"1.0","canonical_sha256":"0277c55b44d7c45ddc542e5059935fa81817d0d560db10f3f2696d489f45fa96","source":{"kind":"arxiv","id":"2403.11780","version":3},"attestation_state":"computed","paper":{"title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fuming You, Rongjie Huang, Ruiqi Li, Ruofan Hu, Tao Jin, Wenrui Liu, Yongqi Wang, Zhiqing Hong, Zhou Zhao","submitted_at":"2024-03-18T13:39:05Z","abstract_excerpt":"Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we ex"},"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":"2403.11780","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-03-18T13:39:05Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"19e5b8840b8414629cf787abafd6746e648e70c2142ba47391db69864b648508","abstract_canon_sha256":"01e46b2105038a98cafde86c5d562fb49395fdbae3c9e756969c316d98348137"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:19.701902Z","signature_b64":"2tCNqHXoCo2SpgVgCB+xmDzCMxOB6iyKwpFkgw31Q0ox+v/XcrxBozeoIXvLyLO5zMo9z7hSM9kT7NSI9E+kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0277c55b44d7c45ddc542e5059935fa81817d0d560db10f3f2696d489f45fa96","last_reissued_at":"2026-07-05T09:57:19.701380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:19.701380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fuming You, Rongjie Huang, Ruiqi Li, Ruofan Hu, Tao Jin, Wenrui Liu, Yongqi Wang, Zhiqing Hong, Zhou Zhao","submitted_at":"2024-03-18T13:39:05Z","abstract_excerpt":"Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11780","kind":"arxiv","version":3},"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/2403.11780/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":"2403.11780","created_at":"2026-07-05T09:57:19.701465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11780v3","created_at":"2026-07-05T09:57:19.701465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11780","created_at":"2026-07-05T09:57:19.701465+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJ34KW2E27CF","created_at":"2026-07-05T09:57:19.701465+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJ34KW2E27CF3XCU","created_at":"2026-07-05T09:57:19.701465+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJ34KW2E","created_at":"2026-07-05T09:57:19.701465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA","json":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA.json","graph_json":"https://pith.science/api/pith-number/AJ34KW2E27CF3XCUFZIFTE27VA/graph.json","events_json":"https://pith.science/api/pith-number/AJ34KW2E27CF3XCUFZIFTE27VA/events.json","paper":"https://pith.science/paper/AJ34KW2E"},"agent_actions":{"view_html":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA","download_json":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA.json","view_paper":"https://pith.science/paper/AJ34KW2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11780&json=true","fetch_graph":"https://pith.science/api/pith-number/AJ34KW2E27CF3XCUFZIFTE27VA/graph.json","fetch_events":"https://pith.science/api/pith-number/AJ34KW2E27CF3XCUFZIFTE27VA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA/action/storage_attestation","attest_author":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA/action/author_attestation","sign_citation":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA/action/citation_signature","submit_replication":"https://pith.science/pith/AJ34KW2E27CF3XCUFZIFTE27VA/action/replication_record"}},"created_at":"2026-07-05T09:57:19.701465+00:00","updated_at":"2026-07-05T09:57:19.701465+00:00"}