{"id":"https://openalex.org/W3015829441","doi":"https://doi.org/10.1109/icassp40776.2020.9053442","title":"Disentangled Multidimensional Metric Learning for Music Similarity","display_name":"Disentangled Multidimensional Metric Learning for Music Similarity","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015829441","doi":"https://doi.org/10.1109/icassp40776.2020.9053442","mag":"3015829441"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5049268304","display_name":"Jongpil Lee","orcid":"https://orcid.org/0000-0002-1126-0081"},"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":"Jongpil Lee","raw_affiliation_strings":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045694117","display_name":"Nicholas J. Bryan","orcid":"https://orcid.org/0000-0003-1469-7278"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas J. Bryan","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037548450","display_name":"Justin Salamon","orcid":"https://orcid.org/0000-0001-6345-4593"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Salamon","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research, San Francisco, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"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":["Graduate School of Culture Technology, KAIST, Daejeon, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6","last_page":"10"},"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":0.995199978351593,"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/T10860","display_name":"Speech and Audio Processing","score":0.989799976348877,"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/similarity","display_name":"Similarity (geometry)","score":0.8349694609642029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7576817870140076},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7496045231819153},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6402701735496521},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5288736820220947},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4541584253311157},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.376708447933197},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3606337308883667},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3295586109161377},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11274862289428711}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8349694609642029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576817870140076},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7496045231819153},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6402701735496521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5288736820220947},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4541584253311157},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.376708447933197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3606337308883667},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3295586109161377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11274862289428711},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053442","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053442","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1531663008","https://openalex.org/W1556219185","https://openalex.org/W1576578512","https://openalex.org/W1836320737","https://openalex.org/W1915070853","https://openalex.org/W1975517671","https://openalex.org/W2038678505","https://openalex.org/W2097117768","https://openalex.org/W2126410803","https://openalex.org/W2191779130","https://openalex.org/W2194775991","https://openalex.org/W2402347808","https://openalex.org/W2405656250","https://openalex.org/W2405905263","https://openalex.org/W2591719913","https://openalex.org/W2592168896","https://openalex.org/W2752782242","https://openalex.org/W2767754137","https://openalex.org/W2935162632","https://openalex.org/W2954224973","https://openalex.org/W2955142818","https://openalex.org/W2963258075","https://openalex.org/W2963420686","https://openalex.org/W2963451564","https://openalex.org/W2963707325","https://openalex.org/W2963775347","https://openalex.org/W2964121744","https://openalex.org/W2990796920","https://openalex.org/W3105202226","https://openalex.org/W4238344759","https://openalex.org/W6631190155","https://openalex.org/W6631829595","https://openalex.org/W6634496701","https://openalex.org/W6638787421","https://openalex.org/W6687152286","https://openalex.org/W6713424904","https://openalex.org/W6745586488","https://openalex.org/W6765018989","https://openalex.org/W6765174816"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2357241418","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W2974225181","https://openalex.org/W4288108740","https://openalex.org/W2153717697"],"abstract_inverted_index":{"Music":[0,48],"similarity":[1,40,62,84,91,99,114,147],"search":[2],"is":[3,34,51,162],"useful":[4],"for":[5],"a":[6,21,24,39,94,106,155],"variety":[7],"of":[8,61,82,108,130],"creative":[9],"tasks":[10],"such":[11],"as":[12,167],"replacing":[13],"one":[14,44],"music":[15],"recording":[16,19,45],"with":[17,20],"another":[18],"similar":[22],"\"feel\",":[23],"common":[25],"task":[26],"in":[27],"video":[28],"editing.":[29],"For":[30],"this":[31,72,76],"task,":[32],"it":[33,122],"typically":[35],"necessary":[36],"to":[37,42,46,53,116,126],"define":[38,54],"metric":[41,110],"compare":[43],"another.":[47],"similarity,":[49],"however,":[50],"hard":[52],"and":[55,78,85,89,120,137,149,157],"depends":[56],"on":[57],"multiple":[58],"simultaneous":[59],"notions":[60],"(i.e.":[63],"genre,":[64],"mood,":[65],"instrument,":[66],"tempo).":[67],"While":[68],"prior":[69],"work":[70],"ignore":[71],"issue,":[73],"we":[74,104],"embrace":[75],"idea":[77],"introduce":[79],"the":[80,117,128],"concept":[81],"multidimensional":[83,98,142],"unify":[86],"both":[87,145],"global":[88],"specialized":[90,146],"metrics":[92],"into":[93],"single,":[95,141],"semantically":[96],"disentangled":[97],"metric.":[100],"To":[101],"do":[102],"so,":[103],"adapt":[105],"variant":[107],"deep":[109],"learning":[111],"called":[112],"conditional":[113],"networks":[115],"audio":[118],"domain":[119],"extend":[121],"using":[123],"track-based":[124],"information":[125],"control":[127],"specificity":[129],"our":[131,135,140,160],"model.":[132],"We":[133,152],"evaluate":[134],"method":[136],"show":[138,158],"that":[139,159],"model":[143],"outperforms":[144],"spaces":[148],"alternative":[150],"baselines.":[151],"also":[153],"run":[154],"user-study":[156],"approach":[161],"favored":[163],"by":[164],"human":[165],"annotators":[166],"well.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":29},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}