{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TBYGUU24PNF75FI7XPTV35WFQQ","short_pith_number":"pith:TBYGUU24","schema_version":"1.0","canonical_sha256":"98706a535c7b4bfe951fbbe75df6c5840f9258765e0d8c0f1c7e054f45606371","source":{"kind":"arxiv","id":"2306.17103","version":4},"attestation_state":"computed","paper":{"title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Emmanouil Benetos, Ge Zhang, Jiahao Pan, Jie Fu, Le Zhuo, Roger Dannenberg, Ruibin Yuan, Si Liu, Wei Xue, Yike Guo, Yinghao Ma, Yizhi Li","submitted_at":"2023-06-29T17:01:51Z","abstract_excerpt":"We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal. Our novel, training-free approach utilizes Whisper, a weakly supervised robust speech recognition model, and GPT-4, today's most performant chat-based large language model. In the proposed method, Whisper functions as the \"ear\" by transcribing the audio, while GPT-4 serves as the \"brain,\" acting as an annotator with a strong performance for contextualized output sel"},"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":"2306.17103","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-29T17:01:51Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3a6570fe7a7e282cf65b9458b914bc4881ab34c54f7c44ef94162e2e0f712ff0","abstract_canon_sha256":"f028a0307546c1f5473748ca68e53e6db502264dc4352c5ebbd797b6d981b41e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:10.721526Z","signature_b64":"RaV6DNEkwTvhp5CknEeaVCtQFujPRABuEM3NUpGDury9jYhyA0ZleFbjWu2jdWpVTDNvpy9x3TQ51T5phl+hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98706a535c7b4bfe951fbbe75df6c5840f9258765e0d8c0f1c7e054f45606371","last_reissued_at":"2026-07-05T08:48:10.721137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:10.721137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenghua Lin, Emmanouil Benetos, Ge Zhang, Jiahao Pan, Jie Fu, Le Zhuo, Roger Dannenberg, Ruibin Yuan, Si Liu, Wei Xue, Yike Guo, Yinghao Ma, Yizhi Li","submitted_at":"2023-06-29T17:01:51Z","abstract_excerpt":"We introduce LyricWhiz, a robust, multilingual, and zero-shot automatic lyrics transcription method achieving state-of-the-art performance on various lyrics transcription datasets, even in challenging genres such as rock and metal. Our novel, training-free approach utilizes Whisper, a weakly supervised robust speech recognition model, and GPT-4, today's most performant chat-based large language model. In the proposed method, Whisper functions as the \"ear\" by transcribing the audio, while GPT-4 serves as the \"brain,\" acting as an annotator with a strong performance for contextualized output sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17103","kind":"arxiv","version":4},"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/2306.17103/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":"2306.17103","created_at":"2026-07-05T08:48:10.721198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17103v4","created_at":"2026-07-05T08:48:10.721198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17103","created_at":"2026-07-05T08:48:10.721198+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBYGUU24PNF7","created_at":"2026-07-05T08:48:10.721198+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBYGUU24PNF75FI7","created_at":"2026-07-05T08:48:10.721198+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBYGUU24","created_at":"2026-07-05T08:48:10.721198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18488","citing_title":"AI-Generated Song Detection via Lyrics Transcripts","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ","json":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ.json","graph_json":"https://pith.science/api/pith-number/TBYGUU24PNF75FI7XPTV35WFQQ/graph.json","events_json":"https://pith.science/api/pith-number/TBYGUU24PNF75FI7XPTV35WFQQ/events.json","paper":"https://pith.science/paper/TBYGUU24"},"agent_actions":{"view_html":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ","download_json":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ.json","view_paper":"https://pith.science/paper/TBYGUU24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17103&json=true","fetch_graph":"https://pith.science/api/pith-number/TBYGUU24PNF75FI7XPTV35WFQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TBYGUU24PNF75FI7XPTV35WFQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ/action/storage_attestation","attest_author":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ/action/author_attestation","sign_citation":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ/action/citation_signature","submit_replication":"https://pith.science/pith/TBYGUU24PNF75FI7XPTV35WFQQ/action/replication_record"}},"created_at":"2026-07-05T08:48:10.721198+00:00","updated_at":"2026-07-05T08:48:10.721198+00:00"}