{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAFMG5IPR6LXEXE4ZHOQTRV3HN","short_pith_number":"pith:EAFMG5IP","schema_version":"1.0","canonical_sha256":"200ac3750f8f97725c9cc9dd09c6bb3b6e607588274a679d60da9dd24e0d8c5d","source":{"kind":"arxiv","id":"2409.06330","version":1},"attestation_state":"computed","paper":{"title":"InstructSing: High-Fidelity Singing Voice Generation via Instructing Yourself","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chang Zeng, Chunhui Wang, Jian Zhao, Xiaoxiao Miao, Yong Chen, Zhonglin Jiang","submitted_at":"2024-09-10T08:38:11Z","abstract_excerpt":"It is challenging to accelerate the training process while ensuring both high-quality generated voices and acceptable inference speed. In this paper, we propose a novel neural vocoder called InstructSing, which can converge much faster compared with other neural vocoders while maintaining good performance by integrating differentiable digital signal processing and adversarial training. It includes one generator and two discriminators. Specifically, the generator incorporates a harmonic-plus-noise (HN) module to produce 8kHz audio as an instructive signal. Subsequently, the HN module is connect"},"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":"2409.06330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-10T08:38:11Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b62cbfeedc7406e49a67152d1265fc271e9b99997377f41342c9ce8157e5fc7a","abstract_canon_sha256":"8590fedc5ce7a5e818f306acbe84d04b6c80011291c20774a3295cef306dcdb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:22.685663Z","signature_b64":"2v2+7vBjhisyE43b7uK5i/c+EHyC1nTGoxpqCtDekqqC86YCPbeiG5F45z1FslfvpP+W4UShzr1SFmaNqxgtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"200ac3750f8f97725c9cc9dd09c6bb3b6e607588274a679d60da9dd24e0d8c5d","last_reissued_at":"2026-07-05T09:05:22.685172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:22.685172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructSing: High-Fidelity Singing Voice Generation via Instructing Yourself","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chang Zeng, Chunhui Wang, Jian Zhao, Xiaoxiao Miao, Yong Chen, Zhonglin Jiang","submitted_at":"2024-09-10T08:38:11Z","abstract_excerpt":"It is challenging to accelerate the training process while ensuring both high-quality generated voices and acceptable inference speed. In this paper, we propose a novel neural vocoder called InstructSing, which can converge much faster compared with other neural vocoders while maintaining good performance by integrating differentiable digital signal processing and adversarial training. It includes one generator and two discriminators. Specifically, the generator incorporates a harmonic-plus-noise (HN) module to produce 8kHz audio as an instructive signal. Subsequently, the HN module is connect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06330","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/2409.06330/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":"2409.06330","created_at":"2026-07-05T09:05:22.685232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06330v1","created_at":"2026-07-05T09:05:22.685232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06330","created_at":"2026-07-05T09:05:22.685232+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAFMG5IPR6LX","created_at":"2026-07-05T09:05:22.685232+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAFMG5IPR6LXEXE4","created_at":"2026-07-05T09:05:22.685232+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAFMG5IP","created_at":"2026-07-05T09:05:22.685232+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/EAFMG5IPR6LXEXE4ZHOQTRV3HN","json":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN.json","graph_json":"https://pith.science/api/pith-number/EAFMG5IPR6LXEXE4ZHOQTRV3HN/graph.json","events_json":"https://pith.science/api/pith-number/EAFMG5IPR6LXEXE4ZHOQTRV3HN/events.json","paper":"https://pith.science/paper/EAFMG5IP"},"agent_actions":{"view_html":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN","download_json":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN.json","view_paper":"https://pith.science/paper/EAFMG5IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06330&json=true","fetch_graph":"https://pith.science/api/pith-number/EAFMG5IPR6LXEXE4ZHOQTRV3HN/graph.json","fetch_events":"https://pith.science/api/pith-number/EAFMG5IPR6LXEXE4ZHOQTRV3HN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN/action/storage_attestation","attest_author":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN/action/author_attestation","sign_citation":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN/action/citation_signature","submit_replication":"https://pith.science/pith/EAFMG5IPR6LXEXE4ZHOQTRV3HN/action/replication_record"}},"created_at":"2026-07-05T09:05:22.685232+00:00","updated_at":"2026-07-05T09:05:22.685232+00:00"}