{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Q5G5B4IH7YDJWQK76DC7FPPD2D","short_pith_number":"pith:Q5G5B4IH","schema_version":"1.0","canonical_sha256":"874dd0f107fe069b415ff0c5f2bde3d0c6132bc5222ea32637656165a2f20997","source":{"kind":"arxiv","id":"1804.05306","version":1},"attestation_state":"computed","paper":{"title":"Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Che-Ping Tsai, Lin-shan Lee, Yi-Lin Tuan","submitted_at":"2018-04-15T05:50:27Z","abstract_excerpt":"Spoken content processing (such as retrieval and browsing) is maturing, but the singing content is still almost completely left out. Songs are human voice carrying plenty of semantic information just as speech, and may be considered as a special type of speech with highly flexible prosody. The various problems in song audio, for example the significantly changing phone duration over highly flexible pitch contours, make the recognition of lyrics from song audio much more difficult. This paper reports an initial attempt towards this goal. We collected music-removed version of English songs direc"},"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":"1804.05306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-04-15T05:50:27Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e97cdcce3501a7f5e71dc6fbee35383211ec6cca88a81bec050bcd92948b4696","abstract_canon_sha256":"a6894ab33f60e576c345ae2b93e3e3e710bf718e0ef47d024a528ae4edf5ae54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:28.391792Z","signature_b64":"Jvta9bUuCcFTjRZ41z+WgsVmcpa0hy3fH2wLRbYx3rT+PLeG5Qzd8g08agNYlKe8LPcUf4WOKVh0pSLb5cliBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874dd0f107fe069b415ff0c5f2bde3d0c6132bc5222ea32637656165a2f20997","last_reissued_at":"2026-05-18T00:18:28.391434Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:28.391434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transcribing Lyrics From Commercial Song Audio: The First Step Towards Singing Content Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Che-Ping Tsai, Lin-shan Lee, Yi-Lin Tuan","submitted_at":"2018-04-15T05:50:27Z","abstract_excerpt":"Spoken content processing (such as retrieval and browsing) is maturing, but the singing content is still almost completely left out. Songs are human voice carrying plenty of semantic information just as speech, and may be considered as a special type of speech with highly flexible prosody. The various problems in song audio, for example the significantly changing phone duration over highly flexible pitch contours, make the recognition of lyrics from song audio much more difficult. This paper reports an initial attempt towards this goal. We collected music-removed version of English songs direc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.05306","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":"1804.05306","created_at":"2026-05-18T00:18:28.391485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.05306v1","created_at":"2026-05-18T00:18:28.391485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.05306","created_at":"2026-05-18T00:18:28.391485+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5G5B4IH7YDJ","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5G5B4IH7YDJWQK7","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5G5B4IH","created_at":"2026-05-18T12:32:46.962924+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/Q5G5B4IH7YDJWQK76DC7FPPD2D","json":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D.json","graph_json":"https://pith.science/api/pith-number/Q5G5B4IH7YDJWQK76DC7FPPD2D/graph.json","events_json":"https://pith.science/api/pith-number/Q5G5B4IH7YDJWQK76DC7FPPD2D/events.json","paper":"https://pith.science/paper/Q5G5B4IH"},"agent_actions":{"view_html":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D","download_json":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D.json","view_paper":"https://pith.science/paper/Q5G5B4IH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.05306&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5G5B4IH7YDJWQK76DC7FPPD2D/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5G5B4IH7YDJWQK76DC7FPPD2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D/action/storage_attestation","attest_author":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D/action/author_attestation","sign_citation":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D/action/citation_signature","submit_replication":"https://pith.science/pith/Q5G5B4IH7YDJWQK76DC7FPPD2D/action/replication_record"}},"created_at":"2026-05-18T00:18:28.391485+00:00","updated_at":"2026-05-18T00:18:28.391485+00:00"}