{"id":"https://openalex.org/W4414426326","doi":"https://doi.org/10.3233/faia250660","title":"Improving AI-Generated Music with User-Guided Training","display_name":"Improving AI-Generated Music with User-Guided Training","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414426326","doi":"https://doi.org/10.3233/faia250660"},"language":"en","primary_location":{"id":"doi:10.3233/faia250660","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250660","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250660","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102702867","display_name":"Vishwa Mohan Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Vishwa Mohan Singh","raw_affiliation_strings":["Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100258040","display_name":"Sai Anirudh Aryasomayajula","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sai Anirudh Aryasomayajula","raw_affiliation_strings":["Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070131856","display_name":"Ahan Chaterjee","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahan Chaterjee","raw_affiliation_strings":["Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119702089","display_name":"Beste Aydemir","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Beste Aydemir","raw_affiliation_strings":["Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073724209","display_name":"Rifat Mehreen Amin","orcid":"https://orcid.org/0000-0003-4279-7778"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rifat Mehreen Amin","raw_affiliation_strings":["Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102702867"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.55268145,"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":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9605000019073486,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9605000019073486,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11309","display_name":"Music and Audio Processing","score":0.9117000102996826,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5683000087738037},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.45829999446868896},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41290000081062317},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.37880000472068787},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.2833999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7175999879837036},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45579999685287476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4546000063419342},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2799000144004822},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250660","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250660","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250660","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250660","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"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":{"AI":[0],"music":[1,70],"generation":[2,82],"has":[3],"advanced":[4],"rapidly,":[5],"with":[6,162],"models":[7],"like":[8],"diffusion":[9],"and":[10,59,74,111],"autoregressive":[11],"algorithms":[12,34,44,101],"enabling":[13],"high-fidelity":[14],"outputs.":[15],"These":[16],"tools":[17],"can":[18,28,35],"alter":[19],"styles,":[20],"mix":[21],"instruments,":[22],"or":[23],"isolate":[24],"them.":[25],"Since":[26],"sound":[27],"be":[29,36],"visualized":[30],"as":[31,117],"spectrograms,":[32],"image-generation":[33],"applied":[37],"to":[38,57,61,94,115,134,180],"generate":[39],"novel":[40],"music.":[41],"However,":[42],"these":[43,100],"are":[45],"typically":[46],"trained":[47,143],"on":[48,103,144],"fixed":[49,146],"datasets,":[50],"which":[51],"makes":[52],"it":[53],"challenging":[54],"for":[55,121],"them":[56],"interpret":[58],"respond":[60],"user":[62,104,113,132,160],"input":[63],"accurately.":[64],"This":[65],"is":[66,71,153],"especially":[67],"problematic":[68],"because":[69],"highly":[72],"subjective":[73],"requires":[75],"a":[76,91,127,140,145],"level":[77],"of":[78,99,139,150,177,194],"personalization":[79],"that":[80,130],"image":[81],"does":[83],"not":[84],"provide.":[85],"In":[86,165],"this":[87,151],"work,":[88],"we":[89],"propose":[90],"human-computation":[92,107],"approach":[93,152],"gradually":[95],"improve":[96],"the":[97,118,123,136,156,166,169,181,197],"performance":[98,138],"based":[102],"interactions.":[105],"The":[106,148,183],"element":[108],"involves":[109],"aggregating":[110],"selecting":[112],"ratings":[114,161],"use":[116],"loss":[119],"function":[120],"fine-tuning":[122],"model.":[124],"We":[125],"employ":[126],"genetic":[128],"algorithm":[129],"incorporates":[131],"feedback":[133],"enhance":[135],"baseline":[137],"model":[141],"initially":[142],"dataset.":[147],"effectiveness":[149],"measured":[154],"by":[155],"average":[157,174],"increase":[158,176,193],"in":[159],"each":[163],"iteration.":[164,199],"pilot":[167],"test,":[168],"first":[170,198],"iteration":[171,185],"showed":[172],"an":[173,191],"rating":[175],"0.2":[178],"compared":[179],"baseline.":[182],"second":[184],"further":[186],"improved":[187],"upon":[188],"this,":[189],"achieving":[190],"additional":[192],"0.39":[195],"over":[196]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}