{"id":"https://openalex.org/W7077971051","doi":"https://doi.org/10.5281/zenodo.16589528","title":"Assessing the Alignment of Valence and Arousal between Text Prompts and the Resulting AI-Generated Music","display_name":"Assessing the Alignment of Valence and Arousal between Text Prompts and the Resulting AI-Generated Music","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W7077971051","doi":"https://doi.org/10.5281/zenodo.16589528"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.16589528","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16589528","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.16589528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hu, Xinyue","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Hu, Xinyue","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sturm, Bob","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sturm, Bob","raw_affiliation_strings":["KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40992145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.699400007724762,"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"}},"topics":[{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.699400007724762,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.027499999850988388,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.01600000075995922,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.7867000102996826},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.6976000070571899},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6420000195503235},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34450000524520874},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.30809998512268066}],"concepts":[{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.7867000102996826},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.6976000070571899},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6420000195503235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4970000088214874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40779998898506165},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4049000144004822},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3743000030517578},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3425999879837036},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C3020774634","wikidata":"https://www.wikidata.org/wiki/Q3113318","display_name":"Emotional valence","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.16589528","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16589528","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.16589528","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.16589528","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":[{"id":"https://metadata.un.org/sdg/4","score":0.44621196389198303,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"\"Prompt-based":[0],"AI":[1,106],"music":[2,11,26,85,107],"generation":[3,108],"platforms":[4,109,129],"provide":[5],"users":[6],"a":[7,62,76,95,147],"way":[8],"to":[9,19,28,40,54,66,81,94,131,136,170],"generate":[10],"audio":[12],"recordings":[13],"by":[14],"giving":[15],"textual":[16],"prompts.":[17,89],"Yet":[18],"be":[20],"studied":[21],"is":[22,183],"how":[23,126],"the":[24,29,42,45,57,118,127,140,153],"generated":[25,58,86,161],"relates":[27],"corresponding":[30],"text":[31,52,73,99,158,179],"prompts":[32,53,132],"in":[33],"terms":[34],"of":[35,51,56,72,97,139,157,178],"sentiment.":[36],"This":[37],"paper":[38],"begins":[39],"examine":[41,114],"alignment":[43],"between":[44,152],"valence":[46,68],"(pleasantness)":[47],"and":[48,69,111,117,124,160],"arousal":[49,70],"(intensity)":[50],"that":[55],"music.":[59],"We":[60,90,113,173],"fine-tune":[61],"masked":[63],"language":[64],"model":[65],"infer":[67],"(V-A)":[71],"prompts,and":[74],"train":[75],"bimodal":[77],"deep":[78],"neural":[79],"network":[80],"predict":[82],"V-A":[83,120,141,155],"for":[84,122,180],"from":[87,103],"those":[88],"apply":[91],"these":[92],"models":[93],"dataset":[96],"6,086":[98],"prompt-music":[100],"pairs":[101,116],"collected":[102],"two":[104,128],"state-of-the-art":[105],"(Suno":[110],"Udio).":[112],"specific":[115,135],"inferred":[119,154],"ratings":[121,156],"them,":[123],"explore":[125],"respond":[130],"involving":[133],"adjectives":[134],"each":[137],"quadrant":[138],"space.":[142],"Our":[143],"preliminary":[144],"results":[145],"indicate":[146],"significant":[148],"but":[149,163],"weak":[150],"correlation":[151],"prompt":[159],"music,":[162],"formal":[164],"human":[165],"listening":[166],"tests":[167],"are":[168],"necessary":[169],"validate":[171],"this.":[172],"find":[174],"some":[175],"clear":[176,185],"examples":[177],"which":[181],"sentiment":[182],"not":[184],"or":[186],"relevant.\"":[187]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}