{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QLYZDMGBT3Z56ZQMNLBXZ24CUF","short_pith_number":"pith:QLYZDMGB","schema_version":"1.0","canonical_sha256":"82f191b0c19ef3df660c6ac37ceb82a1699e795f500bbfd00d49572fe3dcf6af","source":{"kind":"arxiv","id":"2211.02903","version":1},"attestation_state":"computed","paper":{"title":"VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Caixia Gong, Hanzhao Li, Heyang Xue, Lei Xie, Ruixiong Zhang, Tingwei Guo, Yongmao Zhang","submitted_at":"2022-11-05T13:35:00Z","abstract_excerpt":"End-to-end singing voice synthesis (SVS) model VISinger can achieve better performance than the typical two-stage model with fewer parameters. However, VISinger has several problems: text-to-phase problem, the end-to-end model learns the meaningless mapping of text-to-phase; glitches problem, the harmonic components corresponding to the periodic signal of the voiced segment occurs a sudden change with audible artefacts; low sampling rate, the sampling rate of 24KHz does not meet the application needs of high-fidelity generation with the full-band rate (44.1KHz or higher). In this paper, we pro"},"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":"2211.02903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-05T13:35:00Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"008587393a0af269e28c22eb84d5feb26f15aa39403b5f55e23e0e7ab25f517e","abstract_canon_sha256":"b7d1a34c4709865568acc44514d1907ce053ce762df796e40ca68d2349529c8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:42.051595Z","signature_b64":"nZ+TYONQkJKR7uzEnYulhF5DX9EWCHS/JVmelSzlNIX6RamRBEJ1fdyK/sufiM0qqlqpCKic8OFkT3rFlBuSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82f191b0c19ef3df660c6ac37ceb82a1699e795f500bbfd00d49572fe3dcf6af","last_reissued_at":"2026-07-05T05:13:42.051193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:42.051193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Caixia Gong, Hanzhao Li, Heyang Xue, Lei Xie, Ruixiong Zhang, Tingwei Guo, Yongmao Zhang","submitted_at":"2022-11-05T13:35:00Z","abstract_excerpt":"End-to-end singing voice synthesis (SVS) model VISinger can achieve better performance than the typical two-stage model with fewer parameters. However, VISinger has several problems: text-to-phase problem, the end-to-end model learns the meaningless mapping of text-to-phase; glitches problem, the harmonic components corresponding to the periodic signal of the voiced segment occurs a sudden change with audible artefacts; low sampling rate, the sampling rate of 24KHz does not meet the application needs of high-fidelity generation with the full-band rate (44.1KHz or higher). In this paper, we pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02903","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/2211.02903/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":"2211.02903","created_at":"2026-07-05T05:13:42.051248+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02903v1","created_at":"2026-07-05T05:13:42.051248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02903","created_at":"2026-07-05T05:13:42.051248+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLYZDMGBT3Z5","created_at":"2026-07-05T05:13:42.051248+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLYZDMGBT3Z56ZQM","created_at":"2026-07-05T05:13:42.051248+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLYZDMGB","created_at":"2026-07-05T05:13:42.051248+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":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05526","citing_title":"Controllable Singing Style Conversion with Boundary-Aware Information Bottleneck","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF","json":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF.json","graph_json":"https://pith.science/api/pith-number/QLYZDMGBT3Z56ZQMNLBXZ24CUF/graph.json","events_json":"https://pith.science/api/pith-number/QLYZDMGBT3Z56ZQMNLBXZ24CUF/events.json","paper":"https://pith.science/paper/QLYZDMGB"},"agent_actions":{"view_html":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF","download_json":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF.json","view_paper":"https://pith.science/paper/QLYZDMGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02903&json=true","fetch_graph":"https://pith.science/api/pith-number/QLYZDMGBT3Z56ZQMNLBXZ24CUF/graph.json","fetch_events":"https://pith.science/api/pith-number/QLYZDMGBT3Z56ZQMNLBXZ24CUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF/action/storage_attestation","attest_author":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF/action/author_attestation","sign_citation":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF/action/citation_signature","submit_replication":"https://pith.science/pith/QLYZDMGBT3Z56ZQMNLBXZ24CUF/action/replication_record"}},"created_at":"2026-07-05T05:13:42.051248+00:00","updated_at":"2026-07-05T05:13:42.051248+00:00"}