{"id":"https://openalex.org/W7108665777","doi":"https://doi.org/10.5281/zenodo.17811328","title":"AI-Generated Song Detection via Lyrics Transcripts","display_name":"AI-Generated Song Detection via Lyrics Transcripts","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108665777","doi":"https://doi.org/10.5281/zenodo.17811328"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811328","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811328","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.17811328","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Markus Frohmann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus Frohmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Elena Epure","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Epure","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gabriel Meseguer Brocal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Meseguer Brocal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Markus Schedl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Markus Schedl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Romain Hennequin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Hennequin","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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8337000012397766,"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":0.8337000012397766,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.022700000554323196,"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/T10028","display_name":"Topic Modeling","score":0.015799999237060547,"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":0.9911999702453613},{"id":"https://openalex.org/keywords/popular-music","display_name":"Popular music","score":0.33230000734329224},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.32339999079704285},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.28279998898506165}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9911999702453613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604999899864197},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6140999794006348},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4580000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C114611597","wikidata":"https://www.wikidata.org/wiki/Q373342","display_name":"Popular music","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.32339999079704285},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.302700012922287},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811328","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811328","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.17811328","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811328","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,143],"recent":[1,57],"rise":[2],"in":[3,14,76,93,95,124,190],"capabilities":[4],"of":[5,22],"AI-based":[6],"music":[7,17,198],"generation":[8],"tools":[9],"has":[10,39],"created":[11],"an":[12],"upheaval":[13],"the":[15,20,52,85,186],"entire":[16],"industry,":[18],"necessitating":[19],"creation":[21],"accurate":[23,60],"methods":[24,133],"to":[25,45,47,71],"detect":[26,72],"such":[27,78],"AI-generated":[28,73,130],"content.":[29],"This":[30],"can":[31,134],"be":[32,135],"done":[33],"using":[34,111,140,165],"audio-based":[35,183],"detectors;":[36],"however,":[37],"it":[38],"been":[40],"shown":[41],"that":[42,175],"they":[43],"struggle":[44],"generalize":[46],"unseen":[48],"generators":[49],"or":[50],"when":[51,185,194],"audio":[53,86,187],"is":[54,178,188],"perturbed.":[55],"Furthermore,":[56],"work":[58],"used":[59],"and":[61,128,148,158,168,193],"cleanly":[62],"formatted":[63],"lyrics":[64,68,80,120,150],"sourced":[65],"from":[66],"a":[67,90,125],"provider":[69],"database":[70],"music.":[74],"However,":[75],"practice,":[77],"perfect":[79],"are":[81,121],"not":[82],"available":[83,123],"(only":[84],"is);":[87],"this":[88,100,106,139],"leaves":[89],"substantial":[91],"gap":[92,107],"applicability":[94],"real-life":[96],"use":[97],"cases.":[98],"In":[99,171],"work,":[101],"we":[102,173],"instead":[103],"propose":[104],"solving":[105],"by":[108],"transcribing":[109],"songs":[110],"general":[112],"automatic":[113],"speech":[114],"recognition":[115],"(ASR)":[116],"models.":[117],"Once":[118],"transcribed,":[119],"again":[122],"text":[126,131],"representation,":[127],"established":[129],"detection":[132,154],"applied.":[136],"We":[137],"do":[138],"several":[141],"detectors.":[142],"results":[144],"on":[145,196],"diverse,":[146],"multi-genre,":[147],"multi-lingual":[149],"show":[151,174],"generally":[152],"strong":[153],"performance":[155],"across":[156],"languages":[157],"genres,":[159],"particularly":[160],"for":[161],"our":[162,176],"best-performing":[163],"model":[164],"Whisper":[166],"large-v2":[167],"LLM2Vec":[169],"embeddings.":[170],"addition,":[172],"method":[177],"more":[179],"robust":[180],"than":[181],"state-of-the-art":[182],"ones":[184],"perturbed":[189],"different":[191,197],"ways":[192],"evaluated":[195],"generators.":[199]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-12-05T00:00:00"}