{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6BT7RQZHQRQNLDNZEMWTJ7TPBF","short_pith_number":"pith:6BT7RQZH","schema_version":"1.0","canonical_sha256":"f067f8c3278460d58db9232d34fe6f0965884f135df3196697cbc3e481cbdb6b","source":{"kind":"arxiv","id":"2203.12053","version":1},"attestation_state":"computed","paper":{"title":"Upmixing via style transfer: a variational autoencoder for disentangling spatial images and musical content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haici Yang, Mike Luo, Minje Kim, Sanna Wager, Spencer Russell, Wontak Kim","submitted_at":"2022-03-22T21:25:18Z","abstract_excerpt":"In the stereo-to-multichannel upmixing problem for music, one of the main tasks is to set the directionality of the instrument sources in the multichannel rendering results. In this paper, we propose a modified variational autoencoder model that learns a latent space to describe the spatial images in multichannel music. We seek to disentangle the spatial images and music content, so the learned latent variables are invariant to the music. At test time, we use the latent variables to control the panning of sources. We propose two upmixing use cases: transferring the spatial images from one song"},"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":"2203.12053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-22T21:25:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"914ce3b3189821c55558d46d765fab7fb961d04cd1c8284210dd38df6f7ff673","abstract_canon_sha256":"1dbfe478bf68e7bf3d917e8cc5485458492b4dc9f4dfaa8fc79ef97c1ed90db0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:55.488680Z","signature_b64":"3aWTuit/oX0Knbzxag0B6heR01tq4a4w7butUGN6sRe2VBnjfJWad8PDd0+CnpTOkkQxDbSVYHh/FTt+spr2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f067f8c3278460d58db9232d34fe6f0965884f135df3196697cbc3e481cbdb6b","last_reissued_at":"2026-07-05T04:07:55.488213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:55.488213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Upmixing via style transfer: a variational autoencoder for disentangling spatial images and musical content","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haici Yang, Mike Luo, Minje Kim, Sanna Wager, Spencer Russell, Wontak Kim","submitted_at":"2022-03-22T21:25:18Z","abstract_excerpt":"In the stereo-to-multichannel upmixing problem for music, one of the main tasks is to set the directionality of the instrument sources in the multichannel rendering results. In this paper, we propose a modified variational autoencoder model that learns a latent space to describe the spatial images in multichannel music. We seek to disentangle the spatial images and music content, so the learned latent variables are invariant to the music. At test time, we use the latent variables to control the panning of sources. We propose two upmixing use cases: transferring the spatial images from one song"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12053","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/2203.12053/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":"2203.12053","created_at":"2026-07-05T04:07:55.488265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.12053v1","created_at":"2026-07-05T04:07:55.488265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12053","created_at":"2026-07-05T04:07:55.488265+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BT7RQZHQRQN","created_at":"2026-07-05T04:07:55.488265+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BT7RQZHQRQNLDNZ","created_at":"2026-07-05T04:07:55.488265+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BT7RQZH","created_at":"2026-07-05T04:07:55.488265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF","json":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF.json","graph_json":"https://pith.science/api/pith-number/6BT7RQZHQRQNLDNZEMWTJ7TPBF/graph.json","events_json":"https://pith.science/api/pith-number/6BT7RQZHQRQNLDNZEMWTJ7TPBF/events.json","paper":"https://pith.science/paper/6BT7RQZH"},"agent_actions":{"view_html":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF","download_json":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF.json","view_paper":"https://pith.science/paper/6BT7RQZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.12053&json=true","fetch_graph":"https://pith.science/api/pith-number/6BT7RQZHQRQNLDNZEMWTJ7TPBF/graph.json","fetch_events":"https://pith.science/api/pith-number/6BT7RQZHQRQNLDNZEMWTJ7TPBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF/action/storage_attestation","attest_author":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF/action/author_attestation","sign_citation":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF/action/citation_signature","submit_replication":"https://pith.science/pith/6BT7RQZHQRQNLDNZEMWTJ7TPBF/action/replication_record"}},"created_at":"2026-07-05T04:07:55.488265+00:00","updated_at":"2026-07-05T04:07:55.488265+00:00"}