{"id":"https://openalex.org/W4392908974","doi":"https://doi.org/10.1109/icassp48485.2024.10446380","title":"Enriching Music Descriptions with A Finetuned-LLM and Metadata for Text-to-Music Retrieval","display_name":"Enriching Music Descriptions with A Finetuned-LLM and Metadata for Text-to-Music Retrieval","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908974","doi":"https://doi.org/10.1109/icassp48485.2024.10446380"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446380","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":"article","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/A5010952526","display_name":"SeungHeon Doh","orcid":"https://orcid.org/0000-0002-8448-9928"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"SeungHeon Doh","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,South Korea","Graduate School of Culture Technology, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100784269","display_name":"Min\u2010Hee Lee","orcid":"https://orcid.org/0000-0002-1932-9557"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhee Lee","raw_affiliation_strings":["Sogang University,Department of Computer Science and Engineering,South Korea","Department of Computer Science and Engineering, Sogang University, South Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Computer Science and Engineering,South Korea","institution_ids":["https://openalex.org/I148751991"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055794128","display_name":"Dasaem Jeong","orcid":"https://orcid.org/0009-0002-3655-1181"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dasaem Jeong","raw_affiliation_strings":["Sogang University,Department of Art &amp; Technology,South Korea"],"affiliations":[{"raw_affiliation_string":"Sogang University,Department of Art &amp; Technology,South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,South Korea","Graduate School of Culture Technology, KAIST, South Korea"],"affiliations":[{"raw_affiliation_string":"KAIST,Graduate School of Culture Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010952526"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.4963,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.89434122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"826","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9699000120162964,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8521946668624878},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.810936689376831},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6332457065582275},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4264974594116211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521946668624878},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.810936689376831},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6332457065582275},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4264974594116211}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446380","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2116373735","https://openalex.org/W2593116425","https://openalex.org/W2842511635","https://openalex.org/W2965373594","https://openalex.org/W2970641574","https://openalex.org/W3015829441","https://openalex.org/W3045349544","https://openalex.org/W3162583214","https://openalex.org/W3168867926","https://openalex.org/W4226278401","https://openalex.org/W4297808394","https://openalex.org/W4318351475","https://openalex.org/W4319989813","https://openalex.org/W4372259760","https://openalex.org/W4372259983","https://openalex.org/W4372260310","https://openalex.org/W4384918448","https://openalex.org/W4385848641","https://openalex.org/W4386076057","https://openalex.org/W4392963916","https://openalex.org/W4400033239","https://openalex.org/W6633499030","https://openalex.org/W6732646663","https://openalex.org/W6761205521","https://openalex.org/W6765174816","https://openalex.org/W6766673545","https://openalex.org/W6791192960","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6799681646","https://openalex.org/W6803088475","https://openalex.org/W6810738896","https://openalex.org/W6841982715","https://openalex.org/W6843026064","https://openalex.org/W6849105126","https://openalex.org/W6849635556","https://openalex.org/W6852147771","https://openalex.org/W6854866820","https://openalex.org/W6855639150","https://openalex.org/W6855932524","https://openalex.org/W6858779713"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010"],"abstract_inverted_index":{"Text-to-Music":[0,103],"Retrieval,":[1],"finding":[2],"music":[3,20,36,44,72,136],"based":[4],"on":[5,31],"a":[6,12,32,68,86,116,142,167],"given":[7],"natural":[8],"language":[9,119],"query,":[10],"plays":[11],"pivotal":[13],"role":[14],"in":[15,158],"content":[16],"discovery":[17],"within":[18],"extensive":[19],"databases.":[21],"To":[22,94,123],"address":[23,95],"this":[24,98],"challenge,":[25],"prior":[26],"research":[27],"has":[28],"predominantly":[29],"focused":[30],"joint":[33,163],"embedding":[34,164],"of":[35,130,146,156],"audio":[37],"and":[38,58,121,138,141,148],"text,":[39],"utilizing":[40],"it":[41],"to":[42,52,70,89,160],"retrieve":[43],"tracks":[45,79],"that":[46,73],"exactly":[47],"match":[48],"descriptive":[49],"queries":[50],"related":[51],"musical":[53,172],"attributes":[54],"(i.e.":[55,61],"genre,":[56],"instrument)":[57],"contextual":[59],"elements":[60],"mood,":[62],"theme).":[63],"However,":[64],"users":[65],"also":[66],"articulate":[67],"need":[69,85],"explore":[71],"shares":[74],"similarities":[75],"with":[76,115],"their":[77],"favorite":[78],"or":[80],"artists,":[81],"such":[82],"as":[83,107],"I":[84],"similar":[87],"track":[88],"Superstition":[90],"by":[91],"Stevie":[92],"Wonder.":[93],"these":[96],"concerns,":[97],"paper":[99],"proposes":[100],"an":[101],"improved":[102],"Retrieval":[104],"model,":[105],"denoted":[106],"TTMR++,":[108],"which":[109],"utilizes":[110],"rich":[111],"text":[112,132,173],"descriptions":[113],"generated":[114],"finetuned":[117],"large":[118],"model":[120],"metadata.":[122],"accomplish":[124],"this,":[125],"we":[126],"obtained":[127],"various":[128,171],"types":[129],"seed":[131],"from":[133],"several":[134],"existing":[135],"tag":[137],"caption":[139],"datasets":[140],"knowledge":[143],"graph":[144],"dataset":[145],"artists":[147],"tracks.":[149],"The":[150],"experimental":[151],"results":[152],"show":[153],"the":[154],"effectiveness":[155],"TTMR++":[157],"comparison":[159],"state-of-the-art":[161],"music-text":[162],"models":[165],"through":[166],"comprehensive":[168],"evaluation":[169],"involving":[170],"queries.":[174],"<sup":[175],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[176],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[177]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}