{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BJFSNCG7LNFWKS2EIQNI2BMZUB","short_pith_number":"pith:BJFSNCG7","schema_version":"1.0","canonical_sha256":"0a4b2688df5b4b654b44441a8d0599a04ab659d707de7b9bbfaa8700654bd6d4","source":{"kind":"arxiv","id":"1906.11139","version":1},"attestation_state":"computed","paper":{"title":"Learning a Joint Embedding Space of Monophonic and Mixed Music Signals for Singing Voice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Juhan Nam, Kyungyun Lee","submitted_at":"2019-06-26T14:55:16Z","abstract_excerpt":"Previous approaches in singer identification have used one of monophonic vocal tracks or mixed tracks containing multiple instruments, leaving a semantic gap between these two domains of audio. In this paper, we present a system to learn a joint embedding space of monophonic and mixed tracks for singing voice. We use a metric learning method, which ensures that tracks from both domains of the same singer are mapped closer to each other than those of different singers. We train the system on a large synthetic dataset generated by music mashup to reflect real-world music recordings. Our approach"},"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":"1906.11139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2019-06-26T14:55:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"2f9d34c1da74fc4ee5ac9caf02bbc465bcef37f05aa80a93a0266f862ef8c708","abstract_canon_sha256":"f3ea86bc0889fade9090882c27a74296ff2d384829543601d1c5726231a3d08a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:09.715357Z","signature_b64":"hGwdWWkxnffhVjJOLrc252ADjdqFNyBd0PBxR0TxKqAWzOncIhFO0t5NpC7mww79X204XSG4ON96Iivk148BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a4b2688df5b4b654b44441a8d0599a04ab659d707de7b9bbfaa8700654bd6d4","last_reissued_at":"2026-05-17T23:42:09.714690Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:09.714690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Joint Embedding Space of Monophonic and Mixed Music Signals for Singing Voice","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Juhan Nam, Kyungyun Lee","submitted_at":"2019-06-26T14:55:16Z","abstract_excerpt":"Previous approaches in singer identification have used one of monophonic vocal tracks or mixed tracks containing multiple instruments, leaving a semantic gap between these two domains of audio. In this paper, we present a system to learn a joint embedding space of monophonic and mixed tracks for singing voice. We use a metric learning method, which ensures that tracks from both domains of the same singer are mapped closer to each other than those of different singers. We train the system on a large synthetic dataset generated by music mashup to reflect real-world music recordings. Our approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11139","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":"1906.11139","created_at":"2026-05-17T23:42:09.714796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11139v1","created_at":"2026-05-17T23:42:09.714796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11139","created_at":"2026-05-17T23:42:09.714796+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJFSNCG7LNFW","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJFSNCG7LNFWKS2E","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJFSNCG7","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11139","citing_title":"Learning a Joint Embedding Space of Monophonic and Mixed Music Signals for Singing Voice","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB","json":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB.json","graph_json":"https://pith.science/api/pith-number/BJFSNCG7LNFWKS2EIQNI2BMZUB/graph.json","events_json":"https://pith.science/api/pith-number/BJFSNCG7LNFWKS2EIQNI2BMZUB/events.json","paper":"https://pith.science/paper/BJFSNCG7"},"agent_actions":{"view_html":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB","download_json":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB.json","view_paper":"https://pith.science/paper/BJFSNCG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11139&json=true","fetch_graph":"https://pith.science/api/pith-number/BJFSNCG7LNFWKS2EIQNI2BMZUB/graph.json","fetch_events":"https://pith.science/api/pith-number/BJFSNCG7LNFWKS2EIQNI2BMZUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB/action/storage_attestation","attest_author":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB/action/author_attestation","sign_citation":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB/action/citation_signature","submit_replication":"https://pith.science/pith/BJFSNCG7LNFWKS2EIQNI2BMZUB/action/replication_record"}},"created_at":"2026-05-17T23:42:09.714796+00:00","updated_at":"2026-05-17T23:42:09.714796+00:00"}