{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5RKIDQLPSNXSFA567MHTOSQUHT","short_pith_number":"pith:5RKIDQLP","schema_version":"1.0","canonical_sha256":"ec5481c16f936f2283befb0f374a143ce43733f9ecf93b3ef834c3889f1d1182","source":{"kind":"arxiv","id":"2311.07345","version":2},"attestation_state":"computed","paper":{"title":"Zero-Shot Duet Singing Voices Separation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chin-Yun Yu, Emanuele Rodol\\`a, Emilian Postolache, Gy\\\"orgy Fazekas","submitted_at":"2023-11-13T14:01:21Z","abstract_excerpt":"In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target signal given an observed signal by manipulating the diffusion process. However, when separating audio sources of the same type, such as duet singing voices, the prior learned by the diffusion process may not be sufficient to maintain the consistency of the source identity in the separated audio. For example, the singer may change from one to another occasionally. Tackling this problem will be useful for separating sourc"},"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":"2311.07345","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-11-13T14:01:21Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"5b1823889212cf3f0c1f8da046dc02157996d5802b59ada569efdd06275c0f32","abstract_canon_sha256":"5521762494a06952c8b92ae670e37b403e49f80ffed23173bedd62ee68ccfac8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:01.351896Z","signature_b64":"T5keJ+SNG+Ouyzj9eQimtk001pKThXT90CPRKpumJTxX9lviNsKhRpuYx3GB/+vVbYcHCg2WW04ZsN1OENFtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec5481c16f936f2283befb0f374a143ce43733f9ecf93b3ef834c3889f1d1182","last_reissued_at":"2026-07-05T09:23:01.351417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:01.351417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Duet Singing Voices Separation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chin-Yun Yu, Emanuele Rodol\\`a, Emilian Postolache, Gy\\\"orgy Fazekas","submitted_at":"2023-11-13T14:01:21Z","abstract_excerpt":"In recent studies, diffusion models have shown promise as priors for solving audio inverse problems. These models allow us to sample from the posterior distribution of a target signal given an observed signal by manipulating the diffusion process. However, when separating audio sources of the same type, such as duet singing voices, the prior learned by the diffusion process may not be sufficient to maintain the consistency of the source identity in the separated audio. For example, the singer may change from one to another occasionally. Tackling this problem will be useful for separating sourc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07345","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/2311.07345/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":"2311.07345","created_at":"2026-07-05T09:23:01.351475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07345v2","created_at":"2026-07-05T09:23:01.351475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07345","created_at":"2026-07-05T09:23:01.351475+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RKIDQLPSNXS","created_at":"2026-07-05T09:23:01.351475+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RKIDQLPSNXSFA56","created_at":"2026-07-05T09:23:01.351475+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RKIDQLP","created_at":"2026-07-05T09:23:01.351475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.06965","citing_title":"Improving Music Source Separation with Diffusion and Consistency Refinement","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT","json":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT.json","graph_json":"https://pith.science/api/pith-number/5RKIDQLPSNXSFA567MHTOSQUHT/graph.json","events_json":"https://pith.science/api/pith-number/5RKIDQLPSNXSFA567MHTOSQUHT/events.json","paper":"https://pith.science/paper/5RKIDQLP"},"agent_actions":{"view_html":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT","download_json":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT.json","view_paper":"https://pith.science/paper/5RKIDQLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07345&json=true","fetch_graph":"https://pith.science/api/pith-number/5RKIDQLPSNXSFA567MHTOSQUHT/graph.json","fetch_events":"https://pith.science/api/pith-number/5RKIDQLPSNXSFA567MHTOSQUHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT/action/storage_attestation","attest_author":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT/action/author_attestation","sign_citation":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT/action/citation_signature","submit_replication":"https://pith.science/pith/5RKIDQLPSNXSFA567MHTOSQUHT/action/replication_record"}},"created_at":"2026-07-05T09:23:01.351475+00:00","updated_at":"2026-07-05T09:23:01.351475+00:00"}