{"id":"https://openalex.org/W6893091412","doi":"https://doi.org/10.5281/zenodo.14877443","title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","display_name":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","publication_year":2024,"publication_date":"2024-11-10","ids":{"openalex":"https://openalex.org/W6893091412","doi":"https://doi.org/10.5281/zenodo.14877443"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14877443","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14877443","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ond\u0159ej C\u00edfka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ond\u0159ej C\u00edfka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hendrik Schreiber","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendrik Schreiber","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Luke Miner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luke Miner","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fabian-Robert St\u00f6ter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian-Robert St\u00f6ter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7128000259399414,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.7128000259399414,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.04699999839067459,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.03440000116825104,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.8343999981880188},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7914000153541565},{"id":"https://openalex.org/keywords/punctuation","display_name":"Punctuation","score":0.7872999906539917},{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.6504999995231628},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5101000070571899},{"id":"https://openalex.org/keywords/pace","display_name":"Pace","score":0.47360000014305115},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.3817000091075897}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8343999981880188},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7914000153541565},{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.7872999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006999850273132},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.6504999995231628},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5284000039100647},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5101000070571899},{"id":"https://openalex.org/C2777526511","wikidata":"https://www.wikidata.org/wiki/Q691543","display_name":"Pace","level":2,"score":0.47360000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4343999922275543},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3400000035762787},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C2983335612","wikidata":"https://www.wikidata.org/wiki/Q54277","display_name":"Word processing","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14877443","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14877443","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14877443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Writing":[0],"down":[1],"lyrics":[2,41,83,102],"for":[3,19,101,121],"human":[4],"consumption":[5],"involves":[6],"not":[7,64],"only":[8],"accurately":[9],"capturing":[10],"word":[11],"sequences,":[12],"but":[13],"also":[14],"incorporating":[15],"punctuation":[16],"and":[17,21,32,36,53,67,104,113,135],"formatting":[18],"clarity":[20],"to":[22,56,69,98,111,131],"convey":[23],"contextual":[24],"information.":[25],"This":[26],"includes":[27],"song":[28],"structure,":[29],"emotional":[30],"emphasis,":[31],"contrast":[33],"between":[34],"lead":[35],"background":[37],"vocals.":[38],"While":[39],"automatic":[40],"transcription":[42,84,103,133],"(ALT)":[43],"systems":[44,134],"have":[45,63],"advanced":[46],"beyond":[47],"producing":[48],"unstructured":[49],"strings":[50],"of":[51,92,125],"words":[52],"are":[54],"able":[55],"draw":[57],"on":[58,72],"wider":[59],"context,":[60],"ALT":[61],"benchmarks":[62],"kept":[65],"pace":[66],"continue":[68],"focus":[70],"exclusively":[71],"words.":[73],"To":[74],"address":[75],"this":[76],"gap,":[77],"we":[78],"introduce":[79],"Jam-ALT,":[80],"a":[81,89,147],"comprehensive":[82],"benchmark.":[85],"The":[86],"benchmark":[87,130],"features":[88],"complete":[90],"revision":[91],"the":[93,115,119,123,129],"JamendoLyrics":[94],"dataset,":[95],"in":[96],"adherence":[97],"industry":[99],"standards":[100],"formatting,":[105],"along":[106],"with":[107,146],"evaluation":[108],"metrics":[109],"designed":[110],"capture":[112],"assess":[114],"lyric-specific":[116],"nuances,":[117],"laying":[118],"foundation":[120],"improving":[122],"readability":[124],"lyrics.":[126],"We":[127],"apply":[128],"recent":[132],"present":[136],"additional":[137],"error":[138],"analysis,":[139],"as":[140,142],"well":[141],"an":[143],"experimental":[144],"comparison":[145],"classical":[148],"music":[149],"dataset.":[150]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}