{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:63WD2PTIMGK2QJDSCNVOSG6WRL","short_pith_number":"pith:63WD2PTI","schema_version":"1.0","canonical_sha256":"f6ec3d3e686195a82472136ae91bd68ad2634d8915a9b08d691bd9800f9f825d","source":{"kind":"arxiv","id":"2406.05325","version":1},"attestation_state":"computed","paper":{"title":"LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jie Zhang, Liping Chen, Lirong Dai, Na Li, Rilin Chen, Shihao Chen, Yu Gu","submitted_at":"2024-06-08T02:42:52Z","abstract_excerpt":"Any-to-any singing voice conversion (SVC) is an interesting audio editing technique, aiming to convert the singing voice of one singer into that of another, given only a few seconds of singing data. However, during the conversion process, the issue of timbre leakage is inevitable: the converted singing voice still sounds like the original singer's voice. To tackle this, we propose a latent diffusion model for SVC (LDM-SVC) in this work, which attempts to perform SVC in the latent space using an LDM. We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project"},"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":"2406.05325","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-08T02:42:52Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d99e9bb4e929e791227b8cece451997746451dfa6c9e1a69fd4d446121f0b955","abstract_canon_sha256":"b8823c01d966749c69ab6e243ac76ccfff043b39b57c8476e3da21f174669a46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:03.970699Z","signature_b64":"hBGYHMaToiTKL4i5w4j00fgd4kYd2tQSbS6dIsivMzLFVO7eKX34opKgqGy+XYc4E9+TkBb5gq1NnktaGFuFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ec3d3e686195a82472136ae91bd68ad2634d8915a9b08d691bd9800f9f825d","last_reissued_at":"2026-07-05T08:29:03.970055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:03.970055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LDM-SVC: Latent Diffusion Model Based Zero-Shot Any-to-Any Singing Voice Conversion with Singer Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jie Zhang, Liping Chen, Lirong Dai, Na Li, Rilin Chen, Shihao Chen, Yu Gu","submitted_at":"2024-06-08T02:42:52Z","abstract_excerpt":"Any-to-any singing voice conversion (SVC) is an interesting audio editing technique, aiming to convert the singing voice of one singer into that of another, given only a few seconds of singing data. However, during the conversion process, the issue of timbre leakage is inevitable: the converted singing voice still sounds like the original singer's voice. To tackle this, we propose a latent diffusion model for SVC (LDM-SVC) in this work, which attempts to perform SVC in the latent space using an LDM. We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05325","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/2406.05325/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":"2406.05325","created_at":"2026-07-05T08:29:03.970152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05325v1","created_at":"2026-07-05T08:29:03.970152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05325","created_at":"2026-07-05T08:29:03.970152+00:00"},{"alias_kind":"pith_short_12","alias_value":"63WD2PTIMGK2","created_at":"2026-07-05T08:29:03.970152+00:00"},{"alias_kind":"pith_short_16","alias_value":"63WD2PTIMGK2QJDS","created_at":"2026-07-05T08:29:03.970152+00:00"},{"alias_kind":"pith_short_8","alias_value":"63WD2PTI","created_at":"2026-07-05T08:29:03.970152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12890","citing_title":"DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL","json":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL.json","graph_json":"https://pith.science/api/pith-number/63WD2PTIMGK2QJDSCNVOSG6WRL/graph.json","events_json":"https://pith.science/api/pith-number/63WD2PTIMGK2QJDSCNVOSG6WRL/events.json","paper":"https://pith.science/paper/63WD2PTI"},"agent_actions":{"view_html":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL","download_json":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL.json","view_paper":"https://pith.science/paper/63WD2PTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05325&json=true","fetch_graph":"https://pith.science/api/pith-number/63WD2PTIMGK2QJDSCNVOSG6WRL/graph.json","fetch_events":"https://pith.science/api/pith-number/63WD2PTIMGK2QJDSCNVOSG6WRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL/action/storage_attestation","attest_author":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL/action/author_attestation","sign_citation":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL/action/citation_signature","submit_replication":"https://pith.science/pith/63WD2PTIMGK2QJDSCNVOSG6WRL/action/replication_record"}},"created_at":"2026-07-05T08:29:03.970152+00:00","updated_at":"2026-07-05T08:29:03.970152+00:00"}