{"id":"https://openalex.org/W4372259760","doi":"https://doi.org/10.1109/icassp49357.2023.10094670","title":"Toward Universal Text-To-Music Retrieval","display_name":"Toward Universal Text-To-Music Retrieval","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259760","doi":"https://doi.org/10.1109/icassp49357.2023.10094670"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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":false,"raw_author_name":"SeungHeon Doh","raw_affiliation_strings":["KAIST,Graduate School of Culture Technology,South Korea","Graduate School of Culture Technology, KAIST, South Korea"],"raw_orcid":null,"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/A5041096205","display_name":"Minz Won","orcid":"https://orcid.org/0000-0002-6921-1733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minz Won","raw_affiliation_strings":["ByteDance,USA","ByteDance, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance,USA","institution_ids":[]},{"raw_affiliation_string":"ByteDance, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011038627","display_name":"Keunwoo Choi","orcid":"https://orcid.org/0000-0002-5305-5342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keunwoo Choi","raw_affiliation_strings":["Gaudio Lab,South Korea","Gaudio Lab, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaudio Lab,South Korea","institution_ids":[]},{"raw_affiliation_string":"Gaudio Lab, South Korea","institution_ids":[]}]},{"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10028","display_name":"Topic Modeling","score":0.9979000091552734,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.7921510934829712},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7274402379989624},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6452842950820923},{"id":"https://openalex.org/keywords/text-retrieval","display_name":"Text retrieval","score":0.5921187400817871},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5530503392219543},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5288150310516357},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4788263142108917},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4768073260784149},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.47491559386253357},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.4485003352165222},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.44731247425079346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711252808570862},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07717448472976685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921510934829712},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7274402379989624},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6452842950820923},{"id":"https://openalex.org/C2985933255","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Text retrieval","level":2,"score":0.5921187400817871},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5530503392219543},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5288150310516357},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4788263142108917},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4768073260784149},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.47491559386253357},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4485003352165222},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.44731247425079346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711252808570862},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07717448472976685},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1558543783","https://openalex.org/W2072691998","https://openalex.org/W2116373735","https://openalex.org/W2127870748","https://openalex.org/W2250539671","https://openalex.org/W2414894569","https://openalex.org/W2580221632","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2905804369","https://openalex.org/W2950060770","https://openalex.org/W2952610322","https://openalex.org/W2954224973","https://openalex.org/W2963389687","https://openalex.org/W2981571772","https://openalex.org/W3027728407","https://openalex.org/W3047935656","https://openalex.org/W3162583214","https://openalex.org/W3166396011","https://openalex.org/W3180663620","https://openalex.org/W3214872027","https://openalex.org/W4225314222","https://openalex.org/W4226027884","https://openalex.org/W4286850225","https://openalex.org/W4293342670","https://openalex.org/W4293575120","https://openalex.org/W4297808394","https://openalex.org/W4300957348","https://openalex.org/W4304699761","https://openalex.org/W4308860702","https://openalex.org/W6678969435","https://openalex.org/W6715395060","https://openalex.org/W6732646663","https://openalex.org/W6755207826","https://openalex.org/W6757688812","https://openalex.org/W6763945542","https://openalex.org/W6764373287","https://openalex.org/W6765174816","https://openalex.org/W6781425395","https://openalex.org/W6785211131","https://openalex.org/W6785932716","https://openalex.org/W6791353385","https://openalex.org/W6798597329","https://openalex.org/W6803752119","https://openalex.org/W6804120432","https://openalex.org/W6810319077","https://openalex.org/W6841982715","https://openalex.org/W6843026064"],"related_works":["https://openalex.org/W2083605078","https://openalex.org/W1502028000","https://openalex.org/W2169718841","https://openalex.org/W1998451819","https://openalex.org/W204509384","https://openalex.org/W2367995618","https://openalex.org/W2036614928","https://openalex.org/W2350106110","https://openalex.org/W2393777710","https://openalex.org/W2360192068"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"effective":[3],"design":[4],"choices":[5],"for":[6],"text-to-music":[7,79],"retrieval":[8,13,58,80,85],"systems.":[9],"An":[10],"ideal":[11],"text-based":[12,56],"system":[14,81],"would":[15],"support":[16],"various":[17],"input":[18,50,68],"queries":[19],"such":[20],"as":[21],"pre-defined":[22],"tags,":[23,25],"unseen":[24],"and":[26,71,90,110],"sentence-level":[27,91],"descriptions.":[28],"In":[29],"reality,":[30],"most":[31],"previous":[32],"works":[33],"mainly":[34],"focused":[35],"on":[36],"a":[37,77],"single":[38],"query":[39],"type":[40],"(tag":[41],"or":[42],"sentence)":[43],"which":[44],"may":[45],"not":[46],"generalize":[47],"to":[48,99],"another":[49],"type.":[51],"Hence,":[52],"we":[53],"review":[54],"recent":[55],"music":[57,103],"systems":[59],"using":[60],"our":[61],"proposed":[62,95],"benchmark":[63],"in":[64,87],"two":[65],"main":[66],"aspects:":[67],"text":[69],"representation":[70,97],"training":[72],"objectives.":[73],"Our":[74],"findings":[75],"enable":[76],"universal":[78],"that":[82],"achieves":[83],"comparable":[84],"performances":[86],"both":[88],"tag-":[89],"inputs.":[92],"Furthermore,":[93],"the":[94,108],"multimodal":[96],"generalizes":[98],"9":[100],"different":[101],"downstream":[102],"classification":[104],"tasks.":[105],"We":[106],"present":[107],"code":[109],"demo":[111],"online.1":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
