{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UXKKMTXMV4UHZIWECP4XK3GD7Q","short_pith_number":"pith:UXKKMTXM","schema_version":"1.0","canonical_sha256":"a5d4a64eecaf287ca2c413f9756cc3fc3517e39883dcb5f950fc0ff9e91f48d5","source":{"kind":"arxiv","id":"2501.13870","version":1},"attestation_state":"computed","paper":{"title":"Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Roger B. Dannenberg, Shuqi Dai, Yunyun Wang, Zeyu Jin","submitted_at":"2025-01-23T17:41:40Z","abstract_excerpt":"We propose a unified framework for Singing Voice Synthesis (SVS) and Conversion (SVC), addressing the limitations of existing approaches in cross-domain SVS/SVC, poor output musicality, and scarcity of singing data. Our framework enables control over multiple aspects, including language content based on lyrics, performance attributes based on a musical score, singing style and vocal techniques based on a selector, and voice identity based on a speech sample. The proposed zero-shot learning paradigm consists of one SVS model and two SVC models, utilizing pre-trained content embeddings and a dif"},"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":"2501.13870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-23T17:41:40Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"546f89a2b5da8c7aa90dbbcec85ae246a8d184ae6288e02da00fe49e010dfb19","abstract_canon_sha256":"5c094efccbcc950e1f6fff65030d8b4068048dd0bd2a8c757dac257b6d96d232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:35.441122Z","signature_b64":"pFwS6rubsJTfCm3svEqEwGjoqN1sInrdZAJOyveBJylbcyiKGKEgptD5NcL3tzNZ0KDxu3UyYXdfbBlpE1TCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5d4a64eecaf287ca2c413f9756cc3fc3517e39883dcb5f950fc0ff9e91f48d5","last_reissued_at":"2026-07-05T10:04:35.440786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:35.440786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Roger B. Dannenberg, Shuqi Dai, Yunyun Wang, Zeyu Jin","submitted_at":"2025-01-23T17:41:40Z","abstract_excerpt":"We propose a unified framework for Singing Voice Synthesis (SVS) and Conversion (SVC), addressing the limitations of existing approaches in cross-domain SVS/SVC, poor output musicality, and scarcity of singing data. Our framework enables control over multiple aspects, including language content based on lyrics, performance attributes based on a musical score, singing style and vocal techniques based on a selector, and voice identity based on a speech sample. The proposed zero-shot learning paradigm consists of one SVS model and two SVC models, utilizing pre-trained content embeddings and a dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13870","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/2501.13870/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":"2501.13870","created_at":"2026-07-05T10:04:35.440842+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13870v1","created_at":"2026-07-05T10:04:35.440842+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13870","created_at":"2026-07-05T10:04:35.440842+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXKKMTXMV4UH","created_at":"2026-07-05T10:04:35.440842+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXKKMTXMV4UHZIWE","created_at":"2026-07-05T10:04:35.440842+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXKKMTXM","created_at":"2026-07-05T10:04:35.440842+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q","json":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q.json","graph_json":"https://pith.science/api/pith-number/UXKKMTXMV4UHZIWECP4XK3GD7Q/graph.json","events_json":"https://pith.science/api/pith-number/UXKKMTXMV4UHZIWECP4XK3GD7Q/events.json","paper":"https://pith.science/paper/UXKKMTXM"},"agent_actions":{"view_html":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q","download_json":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q.json","view_paper":"https://pith.science/paper/UXKKMTXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13870&json=true","fetch_graph":"https://pith.science/api/pith-number/UXKKMTXMV4UHZIWECP4XK3GD7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/UXKKMTXMV4UHZIWECP4XK3GD7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q/action/storage_attestation","attest_author":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q/action/author_attestation","sign_citation":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q/action/citation_signature","submit_replication":"https://pith.science/pith/UXKKMTXMV4UHZIWECP4XK3GD7Q/action/replication_record"}},"created_at":"2026-07-05T10:04:35.440842+00:00","updated_at":"2026-07-05T10:04:35.440842+00:00"}