{"id":"https://openalex.org/W4372259862","doi":"https://doi.org/10.1109/icassp49357.2023.10095058","title":"Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity","display_name":"Pre-Training Strategies Using Contrastive Learning and Playlist Information for Music Classification and Similarity","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259862","doi":"https://doi.org/10.1109/icassp49357.2023.10095058"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095058","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":"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/A5085164793","display_name":"Pablo Alonso-Jim\u00e9nez","orcid":"https://orcid.org/0000-0002-4121-5089"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]},{"id":"https://openalex.org/I4210095152","display_name":"Itopia (Switzerland)","ror":"https://ror.org/00k0msf85","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210095152"]}],"countries":["CH","ES"],"is_corresponding":true,"raw_author_name":"Pablo Alonso-Jim\u00e9nez","raw_affiliation_strings":["Utopia Music,Switzerland","Music Technology Group, Universitat Pompeu Fabra, Spain","Utopia Music, Switzerland"],"affiliations":[{"raw_affiliation_string":"Utopia Music,Switzerland","institution_ids":["https://openalex.org/I4210095152"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Utopia Music, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066100176","display_name":"Xavier Favory","orcid":"https://orcid.org/0000-0001-6148-0018"},"institutions":[{"id":"https://openalex.org/I4210095152","display_name":"Itopia (Switzerland)","ror":"https://ror.org/00k0msf85","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210095152"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Xavier Favory","raw_affiliation_strings":["Utopia Music,Switzerland","Utopia Music, Switzerland"],"affiliations":[{"raw_affiliation_string":"Utopia Music,Switzerland","institution_ids":["https://openalex.org/I4210095152"]},{"raw_affiliation_string":"Utopia Music, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051299418","display_name":"Hadrien Foroughmand","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095152","display_name":"Itopia (Switzerland)","ror":"https://ror.org/00k0msf85","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210095152"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hadrien Foroughmand","raw_affiliation_strings":["Utopia Music,Switzerland","Utopia Music, Switzerland"],"affiliations":[{"raw_affiliation_string":"Utopia Music,Switzerland","institution_ids":["https://openalex.org/I4210095152"]},{"raw_affiliation_string":"Utopia Music, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064012548","display_name":"Grigoris Bourdalas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095152","display_name":"Itopia (Switzerland)","ror":"https://ror.org/00k0msf85","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210095152"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Grigoris Bourdalas","raw_affiliation_strings":["Utopia Music,Switzerland","Utopia Music, Switzerland"],"affiliations":[{"raw_affiliation_string":"Utopia Music,Switzerland","institution_ids":["https://openalex.org/I4210095152"]},{"raw_affiliation_string":"Utopia Music, Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Spain","Music Technology Group, Universitat Pompeu Fabra, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023691144","display_name":"Thomas Lidy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095152","display_name":"Itopia (Switzerland)","ror":"https://ror.org/00k0msf85","country_code":"CH","type":"company","lineage":["https://openalex.org/I4210095152"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Thomas Lidy","raw_affiliation_strings":["Utopia Music,Switzerland","Utopia Music, Switzerland"],"affiliations":[{"raw_affiliation_string":"Utopia Music,Switzerland","institution_ids":["https://openalex.org/I4210095152"]},{"raw_affiliation_string":"Utopia Music, Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004451369","display_name":"Dmitry Bogdanov","orcid":"https://orcid.org/0000-0002-9469-0633"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Pompeu Fabra University","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Dmitry Bogdanov","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Spain","Music Technology Group, Universitat Pompeu Fabra, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5085164793"],"corresponding_institution_ids":["https://openalex.org/I170486558","https://openalex.org/I4210095152"],"apc_list":null,"apc_paid":null,"fwci":0.8151,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69971831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9923999905586243,"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/metadata","display_name":"Metadata","score":0.8640238046646118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7907732725143433},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7576571106910706},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5580066442489624},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5577951669692993},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5254113674163818},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4622018337249756},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42171090841293335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4215546250343323},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.25059279799461365},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10030326247215271}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8640238046646118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907732725143433},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7576571106910706},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5580066442489624},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5577951669692993},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5254113674163818},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4622018337249756},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42171090841293335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4215546250343323},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.25059279799461365},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10030326247215271},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095058","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":0.7699999809265137,"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":51,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W2059652044","https://openalex.org/W2127870748","https://openalex.org/W2194775991","https://openalex.org/W2293255527","https://openalex.org/W2414894569","https://openalex.org/W2526050071","https://openalex.org/W2799205108","https://openalex.org/W2892896937","https://openalex.org/W2939574508","https://openalex.org/W2950060770","https://openalex.org/W2955142818","https://openalex.org/W2963707325","https://openalex.org/W2964054038","https://openalex.org/W2964274466","https://openalex.org/W2964695147","https://openalex.org/W3005680577","https://openalex.org/W3011574394","https://openalex.org/W3015523207","https://openalex.org/W3015829441","https://openalex.org/W3026092005","https://openalex.org/W3088409176","https://openalex.org/W3098729331","https://openalex.org/W3139211892","https://openalex.org/W3143852976","https://openalex.org/W3157567100","https://openalex.org/W3162391496","https://openalex.org/W3162993808","https://openalex.org/W3163035491","https://openalex.org/W3180663620","https://openalex.org/W3201143670","https://openalex.org/W4220931296","https://openalex.org/W4221161255","https://openalex.org/W4225314222","https://openalex.org/W4225713393","https://openalex.org/W4287757056","https://openalex.org/W4308860702","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6678969435","https://openalex.org/W6715395060","https://openalex.org/W6745586488","https://openalex.org/W6763945542","https://openalex.org/W6765018989","https://openalex.org/W6766666275","https://openalex.org/W6774314701","https://openalex.org/W6777179611","https://openalex.org/W6779191341","https://openalex.org/W6791537541","https://openalex.org/W6798597329"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2095118173","https://openalex.org/W2382021449","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W2501188010","https://openalex.org/W4387830220","https://openalex.org/W4381714195","https://openalex.org/W3160765307"],"abstract_inverted_index":{"In":[0,54],"this":[1,55,59],"work,":[2],"we":[3,57],"investigate":[4,73],"an":[5],"approach":[6,144],"that":[7,29,47,107],"relies":[8],"on":[9,116,146],"contrastive":[10,30],"learning":[11,31],"and":[12,72,79,99,102,110,124],"music":[13,23,69,93,103,122],"metadata":[14,37],"as":[15,65,136],"a":[16,66],"weak":[17],"source":[18,67],"of":[19,68],"supervision":[20],"to":[21,43,61,76,129],"train":[22],"representation":[24],"models.":[25],"Recent":[26],"studies":[27],"show":[28],"can":[32],"be":[33],"used":[34],"with":[35],"editorial":[36],"(e.g.,":[38],"artist":[39,135],"or":[40],"album":[41],"name)":[42],"learn":[44],"audio":[45],"representations":[46],"are":[48],"useful":[49],"for":[50,92,152],"different":[51],"classification":[52,95,126,150],"tasks.":[53],"paper,":[56],"extend":[58],"idea":[60],"using":[62],"playlist":[63],"data":[64],"similarity":[70,123],"information":[71],"three":[74],"approaches":[75,86],"generate":[77],"anchor":[78,109],"positive":[80,111],"track":[81,112],"pairs.":[82],"We":[83,105],"evaluate":[84],"these":[85],"by":[87,114],"fine-tuning":[88],"the":[89,133],"pre-trained":[90],"models":[91],"multi-label":[94],"tasks":[96],"(genre,":[97],"mood,":[98],"instrument":[100],"tagging)":[101],"similarity.":[104],"find":[106],"creating":[108],"pairs":[113],"relying":[115],"co-occurrences":[117],"in":[118,137],"playlists":[119,147],"provides":[120,148],"better":[121],"competitive":[125],"results":[127],"compared":[128],"choosing":[130],"tracks":[131],"from":[132],"same":[134],"previous":[138],"works.":[139],"Additionally,":[140],"our":[141],"best":[142],"pre-training":[143],"based":[145],"superior":[149],"performance":[151],"most":[153],"datasets.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
