{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NADY224NWFPJXIJTHX3Y5EDUEQ","short_pith_number":"pith:NADY224N","schema_version":"1.0","canonical_sha256":"68078d6b8db15e9ba1333df78e9074242d2ea36ce35702a2b4039089e0a67f87","source":{"kind":"arxiv","id":"1902.06797","version":1},"attestation_state":"computed","paper":{"title":"End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Stoller, Sebastian Ewert, Simon Durand","submitted_at":"2019-02-18T20:53:55Z","abstract_excerpt":"Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications. Compared to text-to-speech alignment, lyrics alignment remains highly challenging, despite many attempts to combine numerous sub-modules including vocal separation and detection in an effort to break down the problem. Furthermore, training required fine-grained annotations to be available in some form. Here, we present a novel system based on a modified Wave-U-Net architecture, which predicts character probabilities directly from raw au"},"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":"1902.06797","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-02-18T20:53:55Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a708c1e11385c8fac0d1707f997455168a08bdd8e59578ae9331543f6de84aaf","abstract_canon_sha256":"f54538b9e50d62aab2399b901287900486e83d1d3a2d74ea519ff9ce59aba75a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:40.789912Z","signature_b64":"ny1wte3/INVbmwbiJTwagK/vcZuC4gIBamSrkl0qjMh5B6BCFsLnXx84D7fFslzweNSTMEgov8d1nWurEcMMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68078d6b8db15e9ba1333df78e9074242d2ea36ce35702a2b4039089e0a67f87","last_reissued_at":"2026-05-17T23:53:40.789434Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:40.789434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end Lyrics Alignment for Polyphonic Music Using an Audio-to-Character Recognition Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daniel Stoller, Sebastian Ewert, Simon Durand","submitted_at":"2019-02-18T20:53:55Z","abstract_excerpt":"Time-aligned lyrics can enrich the music listening experience by enabling karaoke, text-based song retrieval and intra-song navigation, and other applications. Compared to text-to-speech alignment, lyrics alignment remains highly challenging, despite many attempts to combine numerous sub-modules including vocal separation and detection in an effort to break down the problem. Furthermore, training required fine-grained annotations to be available in some form. Here, we present a novel system based on a modified Wave-U-Net architecture, which predicts character probabilities directly from raw au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06797","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":"1902.06797","created_at":"2026-05-17T23:53:40.789511+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.06797v1","created_at":"2026-05-17T23:53:40.789511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06797","created_at":"2026-05-17T23:53:40.789511+00:00"},{"alias_kind":"pith_short_12","alias_value":"NADY224NWFPJ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NADY224NWFPJXIJT","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NADY224N","created_at":"2026-05-18T12:33:24.271573+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/NADY224NWFPJXIJTHX3Y5EDUEQ","json":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ.json","graph_json":"https://pith.science/api/pith-number/NADY224NWFPJXIJTHX3Y5EDUEQ/graph.json","events_json":"https://pith.science/api/pith-number/NADY224NWFPJXIJTHX3Y5EDUEQ/events.json","paper":"https://pith.science/paper/NADY224N"},"agent_actions":{"view_html":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ","download_json":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ.json","view_paper":"https://pith.science/paper/NADY224N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.06797&json=true","fetch_graph":"https://pith.science/api/pith-number/NADY224NWFPJXIJTHX3Y5EDUEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NADY224NWFPJXIJTHX3Y5EDUEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ/action/storage_attestation","attest_author":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ/action/author_attestation","sign_citation":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ/action/citation_signature","submit_replication":"https://pith.science/pith/NADY224NWFPJXIJTHX3Y5EDUEQ/action/replication_record"}},"created_at":"2026-05-17T23:53:40.789511+00:00","updated_at":"2026-05-17T23:53:40.789511+00:00"}