{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LEAJ6SUP567WGLE7X5AIDMYCEJ","short_pith_number":"pith:LEAJ6SUP","schema_version":"1.0","canonical_sha256":"59009f4a8fefbf632c9fbf4081b302224fffd4fad219a0a466fc128fb66b0243","source":{"kind":"arxiv","id":"2007.06486","version":2},"attestation_state":"computed","paper":{"title":"Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Emir Demirel, Simon Dixon, Sven Ahlback","submitted_at":"2020-07-13T16:36:30Z","abstract_excerpt":"Speech recognition is a well developed research field so that the current state of the art systems are being used in many applications in the software industry, yet as by today, there still does not exist such robust system for the recognition of words and sentences from singing voice. This paper proposes a complete pipeline for this task which may commonly be referred as automatic lyrics transcription (ALT). We have trained convolutional time-delay neural networks with self-attention on monophonic karaoke recordings using a sequence classification objective for building the acoustic model. Th"},"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":"2007.06486","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2020-07-13T16:36:30Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"afb6068e1f3f935947336a58d0cf54bc93ef494946e75738bdc9cf298c23a151","abstract_canon_sha256":"3b3d6c91ce6d7e0877131cca1e29104de5b6146855d11e21e1b97bebb62dac8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:49.297018Z","signature_b64":"clRh5+5tGGWIBcpSENDv60Ntg44d9nASZxdLMjWAdYUJUN/Q1TkOEwP1OBFlVdQ2Bt8a4BRe36sOZ0akTjQTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59009f4a8fefbf632c9fbf4081b302224fffd4fad219a0a466fc128fb66b0243","last_reissued_at":"2026-07-05T01:21:49.296575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:49.296575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Emir Demirel, Simon Dixon, Sven Ahlback","submitted_at":"2020-07-13T16:36:30Z","abstract_excerpt":"Speech recognition is a well developed research field so that the current state of the art systems are being used in many applications in the software industry, yet as by today, there still does not exist such robust system for the recognition of words and sentences from singing voice. This paper proposes a complete pipeline for this task which may commonly be referred as automatic lyrics transcription (ALT). We have trained convolutional time-delay neural networks with self-attention on monophonic karaoke recordings using a sequence classification objective for building the acoustic model. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06486","kind":"arxiv","version":2},"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/2007.06486/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":"2007.06486","created_at":"2026-07-05T01:21:49.296632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06486v2","created_at":"2026-07-05T01:21:49.296632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06486","created_at":"2026-07-05T01:21:49.296632+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEAJ6SUP567W","created_at":"2026-07-05T01:21:49.296632+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEAJ6SUP567WGLE7","created_at":"2026-07-05T01:21:49.296632+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEAJ6SUP","created_at":"2026-07-05T01:21:49.296632+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/LEAJ6SUP567WGLE7X5AIDMYCEJ","json":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ.json","graph_json":"https://pith.science/api/pith-number/LEAJ6SUP567WGLE7X5AIDMYCEJ/graph.json","events_json":"https://pith.science/api/pith-number/LEAJ6SUP567WGLE7X5AIDMYCEJ/events.json","paper":"https://pith.science/paper/LEAJ6SUP"},"agent_actions":{"view_html":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ","download_json":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ.json","view_paper":"https://pith.science/paper/LEAJ6SUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06486&json=true","fetch_graph":"https://pith.science/api/pith-number/LEAJ6SUP567WGLE7X5AIDMYCEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LEAJ6SUP567WGLE7X5AIDMYCEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ/action/storage_attestation","attest_author":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ/action/author_attestation","sign_citation":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ/action/citation_signature","submit_replication":"https://pith.science/pith/LEAJ6SUP567WGLE7X5AIDMYCEJ/action/replication_record"}},"created_at":"2026-07-05T01:21:49.296632+00:00","updated_at":"2026-07-05T01:21:49.296632+00:00"}