{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GQX5LUMWDBNRSVDDK45ZTYHKFQ","short_pith_number":"pith:GQX5LUMW","schema_version":"1.0","canonical_sha256":"342fd5d196185b195463573b99e0ea2c266ad44aa6a3e1dc721ef6300f03ff59","source":{"kind":"arxiv","id":"2606.30580","version":1},"attestation_state":"computed","paper":{"title":"MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jaekwon Im, Juhan Nam, Yoonjeong Park","submitted_at":"2026-06-29T17:22:27Z","abstract_excerpt":"Text-based singing voice editing (SVE) aims to revise sung lyrics while preserving the original melody, total duration, and non-edited regions. In this paper, we propose MeloDISinger, a flow-matching-based SVE model for melody-aware and duration-preserving editing. Its core module, MeloDRP, predicts fixed-budget duration ratios, enabling explicit span-wise duration control. For melody-aware duration allocation, MeloDRP fuses phonetic cues with pseudo-MIDI melodic context through cross-attention, while temporal-overlap supervision encourages soft phoneme--note correspondences. We further use a "},"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":"2606.30580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-29T17:22:27Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"170d720d344a98c09d644d81b372dcfd6be825761b8f0a2dea41a8b6cb303581","abstract_canon_sha256":"7158ebc4134ec1a4dadc286e8e6e2e23a3e2c869884f14b23889c7fd6c6ec3ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:18:21.328169Z","signature_b64":"ej7z5jGXn+wOUODytkifNKLHzU19LtZ1By4E1Z3ApnEnFus6R7Hsdv3W7cl6Anmo2hKq2RpJz/q2mRi2s6H4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342fd5d196185b195463573b99e0ea2c266ad44aa6a3e1dc721ef6300f03ff59","last_reissued_at":"2026-06-30T02:18:21.327644Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:18:21.327644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jaekwon Im, Juhan Nam, Yoonjeong Park","submitted_at":"2026-06-29T17:22:27Z","abstract_excerpt":"Text-based singing voice editing (SVE) aims to revise sung lyrics while preserving the original melody, total duration, and non-edited regions. In this paper, we propose MeloDISinger, a flow-matching-based SVE model for melody-aware and duration-preserving editing. Its core module, MeloDRP, predicts fixed-budget duration ratios, enabling explicit span-wise duration control. For melody-aware duration allocation, MeloDRP fuses phonetic cues with pseudo-MIDI melodic context through cross-attention, while temporal-overlap supervision encourages soft phoneme--note correspondences. We further use a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30580","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/2606.30580/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":"2606.30580","created_at":"2026-06-30T02:18:21.327710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30580v1","created_at":"2026-06-30T02:18:21.327710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30580","created_at":"2026-06-30T02:18:21.327710+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQX5LUMWDBNR","created_at":"2026-06-30T02:18:21.327710+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQX5LUMWDBNRSVDD","created_at":"2026-06-30T02:18:21.327710+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQX5LUMW","created_at":"2026-06-30T02:18:21.327710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30580","citing_title":"MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ","json":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ.json","graph_json":"https://pith.science/api/pith-number/GQX5LUMWDBNRSVDDK45ZTYHKFQ/graph.json","events_json":"https://pith.science/api/pith-number/GQX5LUMWDBNRSVDDK45ZTYHKFQ/events.json","paper":"https://pith.science/paper/GQX5LUMW"},"agent_actions":{"view_html":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ","download_json":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ.json","view_paper":"https://pith.science/paper/GQX5LUMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30580&json=true","fetch_graph":"https://pith.science/api/pith-number/GQX5LUMWDBNRSVDDK45ZTYHKFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GQX5LUMWDBNRSVDDK45ZTYHKFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ/action/storage_attestation","attest_author":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ/action/author_attestation","sign_citation":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ/action/citation_signature","submit_replication":"https://pith.science/pith/GQX5LUMWDBNRSVDDK45ZTYHKFQ/action/replication_record"}},"created_at":"2026-06-30T02:18:21.327710+00:00","updated_at":"2026-06-30T02:18:21.327710+00:00"}