{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DTSB5HJ6IUZAOCJ5UJCMUKQLJK","short_pith_number":"pith:DTSB5HJ6","schema_version":"1.0","canonical_sha256":"1ce41e9d3e453207093da244ca2a0b4a8aba4d23ffbb1695c0d71ade6c0e1151","source":{"kind":"arxiv","id":"2503.12388","version":2},"attestation_state":"computed","paper":{"title":"Serenade: A Singing Style Conversion Framework Based On Audio Infilling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lester Phillip Violeta, Tomoki Toda, Wen-Chin Huang","submitted_at":"2025-03-16T07:20:22Z","abstract_excerpt":"We propose Serenade, a novel framework for the singing style conversion (SSC) task. Although singer identity conversion has made great strides in the previous years, converting the singing style of a singer has been an unexplored research area. We find three main challenges in SSC: modeling the target style, disentangling source style, and retaining the source melody. To model the target singing style, we use an audio infilling task by predicting a masked segment of the target mel-spectrogram with a flow-matching model using the complement of the masked target mel-spectrogram along with disent"},"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":"2503.12388","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-03-16T07:20:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"44737334056267af4f8b44e81bf9ed0f4d3c1495f9144c0373ca864b4909c597","abstract_canon_sha256":"53b0f360b8850c6e4b4821ad2239410ff05e974d25afb5c610f1dfd62e4f15c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:44.286306Z","signature_b64":"GPGLTGlH3ZppK1VavMqmcVkjPo154LZ0q7Y5x3zrF6mBswRBO7tMTsU8VAARrqXIN5dv2SmMGROSFbJi6omVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce41e9d3e453207093da244ca2a0b4a8aba4d23ffbb1695c0d71ade6c0e1151","last_reissued_at":"2026-07-05T11:31:44.285766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:44.285766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Serenade: A Singing Style Conversion Framework Based On Audio Infilling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lester Phillip Violeta, Tomoki Toda, Wen-Chin Huang","submitted_at":"2025-03-16T07:20:22Z","abstract_excerpt":"We propose Serenade, a novel framework for the singing style conversion (SSC) task. Although singer identity conversion has made great strides in the previous years, converting the singing style of a singer has been an unexplored research area. We find three main challenges in SSC: modeling the target style, disentangling source style, and retaining the source melody. To model the target singing style, we use an audio infilling task by predicting a masked segment of the target mel-spectrogram with a flow-matching model using the complement of the masked target mel-spectrogram along with disent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12388","kind":"arxiv","version":2},"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/2503.12388/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":"2503.12388","created_at":"2026-07-05T11:31:44.285841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12388v2","created_at":"2026-07-05T11:31:44.285841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12388","created_at":"2026-07-05T11:31:44.285841+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTSB5HJ6IUZA","created_at":"2026-07-05T11:31:44.285841+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTSB5HJ6IUZAOCJ5","created_at":"2026-07-05T11:31:44.285841+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTSB5HJ6","created_at":"2026-07-05T11:31:44.285841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17126","citing_title":"Vibrato Expression Control for Singing Voice Conversion with Improving Independent Control","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05526","citing_title":"Controllable Singing Style Conversion with Boundary-Aware Information Bottleneck","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK","json":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK.json","graph_json":"https://pith.science/api/pith-number/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/graph.json","events_json":"https://pith.science/api/pith-number/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/events.json","paper":"https://pith.science/paper/DTSB5HJ6"},"agent_actions":{"view_html":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK","download_json":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK.json","view_paper":"https://pith.science/paper/DTSB5HJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12388&json=true","fetch_graph":"https://pith.science/api/pith-number/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/graph.json","fetch_events":"https://pith.science/api/pith-number/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/action/storage_attestation","attest_author":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/action/author_attestation","sign_citation":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/action/citation_signature","submit_replication":"https://pith.science/pith/DTSB5HJ6IUZAOCJ5UJCMUKQLJK/action/replication_record"}},"created_at":"2026-07-05T11:31:44.285841+00:00","updated_at":"2026-07-05T11:31:44.285841+00:00"}