{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:54SWWHJY5F72J5TDSPLACAYTN6","short_pith_number":"pith:54SWWHJY","schema_version":"1.0","canonical_sha256":"ef256b1d38e97fa4f66393d60103136f9a8ff3ef7c28402cf7f8446b4ad2ac42","source":{"kind":"arxiv","id":"1812.01278","version":1},"attestation_state":"computed","paper":{"title":"Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Balamurali B.T., Dorien Herremans, Enyan Koh, Kin Wah Edward Lin, Simon Lui","submitted_at":"2018-12-04T08:47:41Z","abstract_excerpt":"Separating a singing voice from its music accompaniment remains an important challenge in the field of music information retrieval. We present a unique neural network approach inspired by a technique that has revolutionized the field of vision: pixel-wise image classification, which we combine with cross entropy loss and pretraining of the CNN as an autoencoder on singing voice spectrograms. The pixel-wise classification technique directly estimates the sound source label for each time-frequency (T-F) bin in our spectrogram image, thus eliminating common pre- and postprocessing tasks. The prop"},"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":"1812.01278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-12-04T08:47:41Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"4946cc63a23000ad6a2f05029e2723241ddbcaa5ecfde87db1c8d7c2c939f37a","abstract_canon_sha256":"9f0d042427849ef13104f541abadecedfcfc1f45e18c4cf7fda2a5b58768100b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:12.900744Z","signature_b64":"QNjSJ238/ttzed3mLiC7mLqSI9JmcoIN8+2v1ymRLhHRbPKPmDl+oCMqCn2CjCKlf5/tyR2p+pA3w4XhFCbFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef256b1d38e97fa4f66393d60103136f9a8ff3ef7c28402cf7f8446b4ad2ac42","last_reissued_at":"2026-05-17T23:59:12.900322Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:12.900322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Singing Voice Separation Using a Deep Convolutional Neural Network Trained by Ideal Binary Mask and Cross Entropy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Balamurali B.T., Dorien Herremans, Enyan Koh, Kin Wah Edward Lin, Simon Lui","submitted_at":"2018-12-04T08:47:41Z","abstract_excerpt":"Separating a singing voice from its music accompaniment remains an important challenge in the field of music information retrieval. We present a unique neural network approach inspired by a technique that has revolutionized the field of vision: pixel-wise image classification, which we combine with cross entropy loss and pretraining of the CNN as an autoencoder on singing voice spectrograms. The pixel-wise classification technique directly estimates the sound source label for each time-frequency (T-F) bin in our spectrogram image, thus eliminating common pre- and postprocessing tasks. The prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01278","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":""},"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":"1812.01278","created_at":"2026-05-17T23:59:12.900381+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01278v1","created_at":"2026-05-17T23:59:12.900381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01278","created_at":"2026-05-17T23:59:12.900381+00:00"},{"alias_kind":"pith_short_12","alias_value":"54SWWHJY5F72","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"54SWWHJY5F72J5TD","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"54SWWHJY","created_at":"2026-05-18T12:32:05.422762+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/54SWWHJY5F72J5TDSPLACAYTN6","json":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6.json","graph_json":"https://pith.science/api/pith-number/54SWWHJY5F72J5TDSPLACAYTN6/graph.json","events_json":"https://pith.science/api/pith-number/54SWWHJY5F72J5TDSPLACAYTN6/events.json","paper":"https://pith.science/paper/54SWWHJY"},"agent_actions":{"view_html":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6","download_json":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6.json","view_paper":"https://pith.science/paper/54SWWHJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01278&json=true","fetch_graph":"https://pith.science/api/pith-number/54SWWHJY5F72J5TDSPLACAYTN6/graph.json","fetch_events":"https://pith.science/api/pith-number/54SWWHJY5F72J5TDSPLACAYTN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6/action/storage_attestation","attest_author":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6/action/author_attestation","sign_citation":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6/action/citation_signature","submit_replication":"https://pith.science/pith/54SWWHJY5F72J5TDSPLACAYTN6/action/replication_record"}},"created_at":"2026-05-17T23:59:12.900381+00:00","updated_at":"2026-05-17T23:59:12.900381+00:00"}