{"id":"https://openalex.org/W4393138539","doi":"https://doi.org/10.1109/icassp48485.2024.10446869","title":"Investigating Personalization Methods in Text to Music Generation","display_name":"Investigating Personalization Methods in Text to Music Generation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4393138539","doi":"https://doi.org/10.1109/icassp48485.2024.10446869"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027227399","display_name":"Manos Plitsis","orcid":null},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Manos Plitsis","raw_affiliation_strings":["Athena Research Center,Institute for Language and Speech Processing,Greece","Department of Informatics and Telecommunications, University of Athens, Greece","Institute for Language and Speech Processing, Athena Research Center, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athena Research Center,Institute for Language and Speech Processing,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013292648","display_name":"Theodoros Kouzelis","orcid":"https://orcid.org/0000-0002-1938-9250"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theodoros Kouzelis","raw_affiliation_strings":["Athena Research Center,Institute for Language and Speech Processing,Greece","Institute for Language and Speech Processing, Athena Research Center, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athena Research Center,Institute for Language and Speech Processing,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085959664","display_name":"Georgios Paraskevopoulos","orcid":"https://orcid.org/0000-0002-1644-8390"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Paraskevopoulos","raw_affiliation_strings":["Athena Research Center,Institute for Language and Speech Processing,Greece","Institute for Language and Speech Processing, Athena Research Center, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athena Research Center,Institute for Language and Speech Processing,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060812182","display_name":"Vassilis Katsouros","orcid":"https://orcid.org/0000-0002-4185-2344"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Katsouros","raw_affiliation_strings":["Athena Research Center,Institute for Language and Speech Processing,Greece","Institute for Language and Speech Processing, Athena Research Center, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athena Research Center,Institute for Language and Speech Processing,Greece","institution_ids":["https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Institute for Language and Speech Processing, Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050734738","display_name":"Yannis Panagakis","orcid":"https://orcid.org/0000-0003-0153-5210"},"institutions":[{"id":"https://openalex.org/I200777214","display_name":"National and Kapodistrian University of Athens","ror":"https://ror.org/04gnjpq42","country_code":"GR","type":"education","lineage":["https://openalex.org/I200777214"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Panagakis","raw_affiliation_strings":["University of Athens,Department of Informatics and Telecommunications,Greece","Archimedes Unit, Athena Research Center, Greece","Department of Informatics and Telecommunications, University of Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Athens,Department of Informatics and Telecommunications,Greece","institution_ids":["https://openalex.org/I200777214"]},{"raw_affiliation_string":"Archimedes Unit, Athena Research Center, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Informatics and Telecommunications, University of Athens, Greece","institution_ids":["https://openalex.org/I200777214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8401,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96830914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1081","last_page":"1085"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9988999962806702,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.841045081615448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795037031173706},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5360695719718933},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4899393916130066},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.46311843395233154},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4338931441307068},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.41334670782089233},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40139585733413696},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.29244059324264526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28241783380508423}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.841045081615448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795037031173706},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5360695719718933},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4899393916130066},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.46311843395233154},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4338931441307068},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.41334670782089233},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40139585733413696},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29244059324264526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28241783380508423},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6276162139","display_name":null,"funder_award_id":"MIS 5154714","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8191762521","display_name":"Performing arts in a new era: AI and XR tools for better understanding, preservation, enjoyment and accessibility","funder_award_id":"101061303","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1538887594","https://openalex.org/W2137637927","https://openalex.org/W2593116425","https://openalex.org/W2972478942","https://openalex.org/W2989265781","https://openalex.org/W3015829441","https://openalex.org/W4212774754","https://openalex.org/W4312933868","https://openalex.org/W4318752004","https://openalex.org/W4372260310","https://openalex.org/W4380136719","https://openalex.org/W4385262478","https://openalex.org/W4385271055","https://openalex.org/W4385535331","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4390872341","https://openalex.org/W6632244161","https://openalex.org/W6763954463","https://openalex.org/W6779823529","https://openalex.org/W6841755765","https://openalex.org/W6849109464","https://openalex.org/W6853096648"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W2032548952"],"abstract_inverted_index":{"In":[0],"this":[1,125],"work,":[2],"we":[3,24,62],"investigate":[4],"the":[5,20,26,30,44,51,130],"personalization":[6,39,106],"of":[7,32,46,124],"text-to-music":[8],"diffusion":[9],"models":[10],"in":[11,19,98],"a":[12,64,85],"few-shot":[13],"setting.":[14],"Motivated":[15],"by":[16],"recent":[17],"advances":[18],"computer":[21],"vision":[22],"domain,":[23],"are":[25,97,127],"first":[27],"to":[28,109,129],"explore":[29],"combination":[31],"pre-trained":[33],"text-to-audio":[34],"diffusers":[35],"with":[36,43,67,100],"two":[37],"established":[38],"methods.":[40],"We":[41,72],"experiment":[42],"effect":[45],"audio-specific":[47],"data":[48],"augmentation":[49],"on":[50],"overall":[52],"system":[53],"performance":[54],"and":[55,69,76,103,121],"assess":[56],"different":[57],"training":[58],"strategies.":[59],"For":[60],"evaluation,":[61,81],"construct":[63],"novel":[65],"dataset":[66],"prompts":[68],"music":[70,112],"clips.":[71],"consider":[73],"both":[74],"embedding-based":[75],"music-specific":[77],"metrics":[78,96],"for":[79,88],"quantitative":[80],"as":[82,84],"well":[83],"user":[86,101],"study":[87,126],"qualitative":[89],"evaluation.":[90],"Our":[91],"analysis":[92],"shows":[93],"that":[94,104],"similarity":[95],"accordance":[99],"preferences":[102],"current":[105],"approaches":[107],"tend":[108],"learn":[110],"rhythmic":[111],"concepts":[113],"more":[114],"easily":[115],"than":[116],"melody.":[117],"The":[118],"code,":[119],"dataset,":[120],"example":[122],"material":[123],"open":[128],"research":[131],"community1.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}