{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OYONTERHFHWN4Y6FMWDIAHQMO3","short_pith_number":"pith:OYONTERH","schema_version":"1.0","canonical_sha256":"761cd9922729ecde63c56586801e0c76c9b1d5192a979c352e09ea74aaf3ebda","source":{"kind":"arxiv","id":"2201.09592","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Clement S. J. Doire, Ga\\\"el Richard, Kilian Schulze-Forster, Liam Kelley, Roland Badeau","submitted_at":"2022-01-24T11:05:30Z","abstract_excerpt":"Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely costly to obtain for musical mixtures. This raises a need for unsupervised methods. We propose a novel unsupervised model-based deep learning approach to musical source separation. Each source is modelled with a differentiable parametric source-filter model. A neural network is trained to reconstruct the observed mixture as a sum of the sources by estimating th"},"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":"2201.09592","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-01-24T11:05:30Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"724fcbdd892624f6ead46f616da8d9291669f294155c25e0d98f6f67fd727058","abstract_canon_sha256":"58b2dc753572d5ad693f42a45443d0e47b4c99382c92d6f6f9f59869026ee86d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:04.586273Z","signature_b64":"uNpYW6QcyMYjYmfMtWnoIy5+7Xp+h9odfgj+HYPgesWf65ofjhlMZf/iqzAo5ADRw9U7KhMpRToz/XwAncB0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"761cd9922729ecde63c56586801e0c76c9b1d5192a979c352e09ea74aaf3ebda","last_reissued_at":"2026-07-05T05:37:04.585758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:04.585758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Music Source Separation Using Differentiable Parametric Source Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Clement S. J. Doire, Ga\\\"el Richard, Kilian Schulze-Forster, Liam Kelley, Roland Badeau","submitted_at":"2022-01-24T11:05:30Z","abstract_excerpt":"Supervised deep learning approaches to underdetermined audio source separation achieve state-of-the-art performance but require a dataset of mixtures along with their corresponding isolated source signals. Such datasets can be extremely costly to obtain for musical mixtures. This raises a need for unsupervised methods. We propose a novel unsupervised model-based deep learning approach to musical source separation. Each source is modelled with a differentiable parametric source-filter model. A neural network is trained to reconstruct the observed mixture as a sum of the sources by estimating th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09592","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/2201.09592/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":"2201.09592","created_at":"2026-07-05T05:37:04.585823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.09592v2","created_at":"2026-07-05T05:37:04.585823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09592","created_at":"2026-07-05T05:37:04.585823+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYONTERHFHWN","created_at":"2026-07-05T05:37:04.585823+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYONTERHFHWN4Y6F","created_at":"2026-07-05T05:37:04.585823+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYONTERH","created_at":"2026-07-05T05:37:04.585823+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05654","citing_title":"Toward a Sparse and Interpretable Audio Codec","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3","json":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3.json","graph_json":"https://pith.science/api/pith-number/OYONTERHFHWN4Y6FMWDIAHQMO3/graph.json","events_json":"https://pith.science/api/pith-number/OYONTERHFHWN4Y6FMWDIAHQMO3/events.json","paper":"https://pith.science/paper/OYONTERH"},"agent_actions":{"view_html":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3","download_json":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3.json","view_paper":"https://pith.science/paper/OYONTERH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.09592&json=true","fetch_graph":"https://pith.science/api/pith-number/OYONTERHFHWN4Y6FMWDIAHQMO3/graph.json","fetch_events":"https://pith.science/api/pith-number/OYONTERHFHWN4Y6FMWDIAHQMO3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3/action/storage_attestation","attest_author":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3/action/author_attestation","sign_citation":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3/action/citation_signature","submit_replication":"https://pith.science/pith/OYONTERHFHWN4Y6FMWDIAHQMO3/action/replication_record"}},"created_at":"2026-07-05T05:37:04.585823+00:00","updated_at":"2026-07-05T05:37:04.585823+00:00"}