{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YWIRI4NYGONKLGAMHHDT2NRHMX","short_pith_number":"pith:YWIRI4NY","schema_version":"1.0","canonical_sha256":"c5911471b8339aa5980c39c73d362765d4e81f1903a1e6ac78186ecd7a7dfc5a","source":{"kind":"arxiv","id":"2401.17619","version":3},"attestation_state":"computed","paper":{"title":"Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiatong Shi, Keyi Zhang, Qin Jin, Shinji Watanabe, Xinyi Bai, Yifeng Yu, Yueqian Lin, Yuning Wu, Yuxun Tang","submitted_at":"2024-01-31T06:17:51Z","abstract_excerpt":"In singing voice synthesis (SVS), generating singing voices from musical scores faces challenges due to limited data availability. This study proposes a unique strategy to address the data scarcity in SVS. We employ an existing singing voice synthesizer for data augmentation, complemented by detailed manual tuning, an approach not previously explored in data curation, to reduce instances of unnatural voice synthesis. This innovative method has led to the creation of two expansive singing voice datasets, ACE-Opencpop and ACE-KiSing, which are instrumental for large-scale, multi-singer voice syn"},"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":"2401.17619","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-31T06:17:51Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5be572ccbdd9f930d73d4c4a2739fba3f114f580289dab760afb069bb607f9c8","abstract_canon_sha256":"d25d1216abfa0df1f02ded40e6f6a791aaa75d8a147c169d35388b8e852bc588"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:11.099745Z","signature_b64":"O9pliWJOSQ5Bd0feqzbjs/S9dO8KX/uz1T2IU48kf03iqvlb9VwKSbWoYAnVcgSMjgSE4FRX8A7QePsQxg6XCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5911471b8339aa5980c39c73d362765d4e81f1903a1e6ac78186ecd7a7dfc5a","last_reissued_at":"2026-07-05T08:31:11.099243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:11.099243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiatong Shi, Keyi Zhang, Qin Jin, Shinji Watanabe, Xinyi Bai, Yifeng Yu, Yueqian Lin, Yuning Wu, Yuxun Tang","submitted_at":"2024-01-31T06:17:51Z","abstract_excerpt":"In singing voice synthesis (SVS), generating singing voices from musical scores faces challenges due to limited data availability. This study proposes a unique strategy to address the data scarcity in SVS. We employ an existing singing voice synthesizer for data augmentation, complemented by detailed manual tuning, an approach not previously explored in data curation, to reduce instances of unnatural voice synthesis. This innovative method has led to the creation of two expansive singing voice datasets, ACE-Opencpop and ACE-KiSing, which are instrumental for large-scale, multi-singer voice syn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17619","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/2401.17619/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":"2401.17619","created_at":"2026-07-05T08:31:11.099300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17619v3","created_at":"2026-07-05T08:31:11.099300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17619","created_at":"2026-07-05T08:31:11.099300+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWIRI4NYGONK","created_at":"2026-07-05T08:31:11.099300+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWIRI4NYGONKLGAM","created_at":"2026-07-05T08:31:11.099300+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWIRI4NY","created_at":"2026-07-05T08:31:11.099300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04613","citing_title":"VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX","json":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX.json","graph_json":"https://pith.science/api/pith-number/YWIRI4NYGONKLGAMHHDT2NRHMX/graph.json","events_json":"https://pith.science/api/pith-number/YWIRI4NYGONKLGAMHHDT2NRHMX/events.json","paper":"https://pith.science/paper/YWIRI4NY"},"agent_actions":{"view_html":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX","download_json":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX.json","view_paper":"https://pith.science/paper/YWIRI4NY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17619&json=true","fetch_graph":"https://pith.science/api/pith-number/YWIRI4NYGONKLGAMHHDT2NRHMX/graph.json","fetch_events":"https://pith.science/api/pith-number/YWIRI4NYGONKLGAMHHDT2NRHMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX/action/storage_attestation","attest_author":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX/action/author_attestation","sign_citation":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX/action/citation_signature","submit_replication":"https://pith.science/pith/YWIRI4NYGONKLGAMHHDT2NRHMX/action/replication_record"}},"created_at":"2026-07-05T08:31:11.099300+00:00","updated_at":"2026-07-05T08:31:11.099300+00:00"}