{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OTVBOIQ5HMPYZCY4AORBWJ2FKK","short_pith_number":"pith:OTVBOIQ5","schema_version":"1.0","canonical_sha256":"74ea17221d3b1f8c8b1c03a21b27455295b554e67c4d629f31a6f41dab34183a","source":{"kind":"arxiv","id":"1908.01919","version":1},"attestation_state":"computed","paper":{"title":"Adversarially Trained End-to-end Korean Singing Voice Synthesis System","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chang-Bin Jeon, Hyeong-Seok Choi, Juheon Lee, Junghyun Koo, Kyogu Lee","submitted_at":"2019-08-06T01:17:44Z","abstract_excerpt":"In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement masking, 2) local conditioning of text and pitch to the super-resolution network, and 3) conditional adversarial training. The proposed system consists of two main modules; a mel-synthesis network that generates a mel-spectrogram from the given input information, and a super-resolution network that upsamples the generated mel-spectrogram into a linear-spectrogram. In the mel-synthesis network, phonetic enhancement ma"},"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":"1908.01919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2019-08-06T01:17:44Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c6d317ec8d479e744221d079f2da7b2e79a6d108641902d27287de23329682da","abstract_canon_sha256":"843ef0b1c0d6c06789cc3bd3c600fdba8c36330f224ed7311b50c9df44ea7239"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:49.332570Z","signature_b64":"6k2t0jfhbjW5zOX5vdD5O/lTXusdxGKf6PQ/NzSzaRS4QpApUwGepKhBkBH9mg1SV/MnfHm4uOrk4G0kTFfMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74ea17221d3b1f8c8b1c03a21b27455295b554e67c4d629f31a6f41dab34183a","last_reissued_at":"2026-07-04T23:51:49.332157Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:49.332157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarially Trained End-to-end Korean Singing Voice Synthesis System","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chang-Bin Jeon, Hyeong-Seok Choi, Juheon Lee, Junghyun Koo, Kyogu Lee","submitted_at":"2019-08-06T01:17:44Z","abstract_excerpt":"In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement masking, 2) local conditioning of text and pitch to the super-resolution network, and 3) conditional adversarial training. The proposed system consists of two main modules; a mel-synthesis network that generates a mel-spectrogram from the given input information, and a super-resolution network that upsamples the generated mel-spectrogram into a linear-spectrogram. In the mel-synthesis network, phonetic enhancement ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01919","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/1908.01919/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":"1908.01919","created_at":"2026-07-04T23:51:49.332214+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01919v1","created_at":"2026-07-04T23:51:49.332214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01919","created_at":"2026-07-04T23:51:49.332214+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTVBOIQ5HMPY","created_at":"2026-07-04T23:51:49.332214+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTVBOIQ5HMPYZCY4","created_at":"2026-07-04T23:51:49.332214+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTVBOIQ5","created_at":"2026-07-04T23:51:49.332214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.01919","citing_title":"Adversarially Trained End-to-end Korean Singing Voice Synthesis System","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK","json":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK.json","graph_json":"https://pith.science/api/pith-number/OTVBOIQ5HMPYZCY4AORBWJ2FKK/graph.json","events_json":"https://pith.science/api/pith-number/OTVBOIQ5HMPYZCY4AORBWJ2FKK/events.json","paper":"https://pith.science/paper/OTVBOIQ5"},"agent_actions":{"view_html":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK","download_json":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK.json","view_paper":"https://pith.science/paper/OTVBOIQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01919&json=true","fetch_graph":"https://pith.science/api/pith-number/OTVBOIQ5HMPYZCY4AORBWJ2FKK/graph.json","fetch_events":"https://pith.science/api/pith-number/OTVBOIQ5HMPYZCY4AORBWJ2FKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK/action/storage_attestation","attest_author":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK/action/author_attestation","sign_citation":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK/action/citation_signature","submit_replication":"https://pith.science/pith/OTVBOIQ5HMPYZCY4AORBWJ2FKK/action/replication_record"}},"created_at":"2026-07-04T23:51:49.332214+00:00","updated_at":"2026-07-04T23:51:49.332214+00:00"}