{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:653MQCVB4I6LC736E7RWZ4T57M","short_pith_number":"pith:653MQCVB","schema_version":"1.0","canonical_sha256":"f776c80aa1e23cb17f7e27e36cf27dfb3bdec7c8b3f5fb9f549057fba808c011","source":{"kind":"arxiv","id":"2409.15977","version":6},"attestation_state":"computed","paper":{"title":"TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changhao Pan, Chuxin Wang, Jinzheng He, Rongjie Huang, Ruiqi Li, Yu Zhang, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-09-24T11:18:09Z","abstract_excerpt":"Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles (including singing method, emotion, rhythm, technique, and pronunciation) from audio and text prompts. However, the multifaceted nature of singing styles poses a significant challenge for effective modeling, transfer, and control. Furthermore, current SVS models often fail to generate singing voices rich in stylistic nuances for unseen singers. To address these challenges, we introduce TCSinger, the first zero-shot SVS model for style transfe"},"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":"2409.15977","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-24T11:18:09Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"d0b4e61a799df3f728a1d3fe2d8a3aa11c7201d00af66c8525ee37808d2a7459","abstract_canon_sha256":"2742abf4766fea2ac9a517e8387b265c1007a8113081a04e2d5c3b8872855147"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:20.414699Z","signature_b64":"FSE8FsxXXR1VbvgOwRr51iO+UndDLQ0XLrcKcRpBVoG/Oz5u43qULsOLNePu5wIAAJAFaIawYEmdqz+orYFRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f776c80aa1e23cb17f7e27e36cf27dfb3bdec7c8b3f5fb9f549057fba808c011","last_reissued_at":"2026-07-05T11:12:20.414197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:20.414197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changhao Pan, Chuxin Wang, Jinzheng He, Rongjie Huang, Ruiqi Li, Yu Zhang, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-09-24T11:18:09Z","abstract_excerpt":"Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles (including singing method, emotion, rhythm, technique, and pronunciation) from audio and text prompts. However, the multifaceted nature of singing styles poses a significant challenge for effective modeling, transfer, and control. Furthermore, current SVS models often fail to generate singing voices rich in stylistic nuances for unseen singers. To address these challenges, we introduce TCSinger, the first zero-shot SVS model for style transfe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15977","kind":"arxiv","version":6},"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/2409.15977/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":"2409.15977","created_at":"2026-07-05T11:12:20.414258+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15977v6","created_at":"2026-07-05T11:12:20.414258+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15977","created_at":"2026-07-05T11:12:20.414258+00:00"},{"alias_kind":"pith_short_12","alias_value":"653MQCVB4I6L","created_at":"2026-07-05T11:12:20.414258+00:00"},{"alias_kind":"pith_short_16","alias_value":"653MQCVB4I6LC736","created_at":"2026-07-05T11:12:20.414258+00:00"},{"alias_kind":"pith_short_8","alias_value":"653MQCVB","created_at":"2026-07-05T11:12:20.414258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05526","citing_title":"Controllable Singing Style Conversion with Boundary-Aware Information Bottleneck","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M","json":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M.json","graph_json":"https://pith.science/api/pith-number/653MQCVB4I6LC736E7RWZ4T57M/graph.json","events_json":"https://pith.science/api/pith-number/653MQCVB4I6LC736E7RWZ4T57M/events.json","paper":"https://pith.science/paper/653MQCVB"},"agent_actions":{"view_html":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M","download_json":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M.json","view_paper":"https://pith.science/paper/653MQCVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15977&json=true","fetch_graph":"https://pith.science/api/pith-number/653MQCVB4I6LC736E7RWZ4T57M/graph.json","fetch_events":"https://pith.science/api/pith-number/653MQCVB4I6LC736E7RWZ4T57M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M/action/storage_attestation","attest_author":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M/action/author_attestation","sign_citation":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M/action/citation_signature","submit_replication":"https://pith.science/pith/653MQCVB4I6LC736E7RWZ4T57M/action/replication_record"}},"created_at":"2026-07-05T11:12:20.414258+00:00","updated_at":"2026-07-05T11:12:20.414258+00:00"}