{"id":"https://openalex.org/W3143852976","doi":"https://doi.org/10.1109/lsp.2021.3071082","title":"Enriched Music Representations With Multiple Cross-Modal Contrastive Learning","display_name":"Enriched Music Representations With Multiple Cross-Modal Contrastive Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3143852976","doi":"https://doi.org/10.1109/lsp.2021.3071082","mag":"3143852976"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2021.3071082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3071082","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.00437","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050623835","display_name":"Andr\u00e9s Ferraro","orcid":"https://orcid.org/0000-0003-1236-2503"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Andres Ferraro","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-1236-2503","affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"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/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Favory","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland"],"raw_orcid":"https://orcid.org/0000-0002-3605-7127","affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028585938","display_name":"Yun-Tae Kim","orcid":"https://orcid.org/0000-0002-9313-976X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuntae Kim","raw_affiliation_strings":["Kakao Corporation, Seogam, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kakao Corporation, Seogam, Korea","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":"Universitat Pompeu Fabra","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":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3736,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88621847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"28","issue":null,"first_page":"733","last_page":"737"},"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":0.9990000128746033,"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":0.9970999956130981,"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":0.8423377275466919},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6747932434082031},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5632829666137695},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5531564354896545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5265876650810242},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5260146260261536},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5219782590866089},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5109445452690125},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4956148862838745},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4861406981945038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4850827753543854},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43999359011650085},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4113360047340393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3686198592185974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33224567770957947},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3215346932411194},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08301949501037598}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8423377275466919},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6747932434082031},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5632829666137695},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5531564354896545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5265876650810242},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5260146260261536},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5219782590866089},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5109445452690125},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4956148862838745},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4861406981945038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4850827753543854},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43999359011650085},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4113360047340393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3686198592185974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33224567770957947},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3215346932411194},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08301949501037598},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/lsp.2021.3071082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2021.3071082","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:repositori-api.upf.edu:10230/47323","is_oa":false,"landing_page_url":"http://hdl.handle.net/10230/47323","pdf_url":null,"source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:arXiv.org:2104.00437","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00437","pdf_url":"https://arxiv.org/pdf/2104.00437","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:zenodo.org:5723442","is_oa":true,"landing_page_url":"https://zenodo.org/record/5723442","pdf_url":"https://zenodo.org/record/5723442","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Signal Processing Letters 28 733-737","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.00437","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.00437","pdf_url":"https://arxiv.org/pdf/2104.00437","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1816425981","display_name":null,"funder_award_id":"957337","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W54887220","https://openalex.org/W1614298861","https://openalex.org/W1690919088","https://openalex.org/W2011700584","https://openalex.org/W2106053110","https://openalex.org/W2118123209","https://openalex.org/W2133824856","https://openalex.org/W2173520492","https://openalex.org/W2593116425","https://openalex.org/W2783457476","https://openalex.org/W2842511635","https://openalex.org/W2890267272","https://openalex.org/W2939574508","https://openalex.org/W2950060770","https://openalex.org/W2954224973","https://openalex.org/W2962904371","https://openalex.org/W2962968152","https://openalex.org/W2963403868","https://openalex.org/W2963684088","https://openalex.org/W2965158072","https://openalex.org/W2972737975","https://openalex.org/W2990796920","https://openalex.org/W3000400453","https://openalex.org/W3005680577","https://openalex.org/W3015310419","https://openalex.org/W3018378048","https://openalex.org/W3022509031","https://openalex.org/W3029858316","https://openalex.org/W3035312337","https://openalex.org/W3047935656","https://openalex.org/W3093563057","https://openalex.org/W3093956526","https://openalex.org/W3095513901","https://openalex.org/W3096655658","https://openalex.org/W3097244964","https://openalex.org/W3100345210","https://openalex.org/W3104805957","https://openalex.org/W3112635029","https://openalex.org/W3116979048","https://openalex.org/W3121195490","https://openalex.org/W3137857706","https://openalex.org/W3160173020","https://openalex.org/W3162391496","https://openalex.org/W3162583214","https://openalex.org/W3163035491","https://openalex.org/W4287635193","https://openalex.org/W4287757056","https://openalex.org/W4287812705","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6600827882","https://openalex.org/W6636510571","https://openalex.org/W6675751002","https://openalex.org/W6685352114","https://openalex.org/W6739901393","https://openalex.org/W6763945542","https://openalex.org/W6765174816","https://openalex.org/W6766776083","https://openalex.org/W6768465061","https://openalex.org/W6774314701","https://openalex.org/W6776700526","https://openalex.org/W6778572914","https://openalex.org/W6779191341","https://openalex.org/W6779653705","https://openalex.org/W6781425395","https://openalex.org/W6784077883","https://openalex.org/W6784260069","https://openalex.org/W6784740471","https://openalex.org/W6785211131","https://openalex.org/W6786091203","https://openalex.org/W6790353341","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W203959209","https://openalex.org/W2110287964","https://openalex.org/W2167701463","https://openalex.org/W4307407935"],"abstract_inverted_index":{"Modeling":[0],"various":[1,30],"aspects":[2],"that":[3,54,70,169],"make":[4],"a":[5,10,67,118,141],"music":[6,78],"piece":[7],"unique":[8],"is":[9,23],"challenging":[11],"task,":[12],"requiring":[13],"the":[14,36,96,106,111,138,153,170,174,178,187],"combination":[15],"of":[16,19,32,74,155,159],"multiple":[17,72,157],"sources":[18,31,158],"information.":[20],"Deep":[21],"learning":[22,49],"commonly":[24],"used":[25],"to":[26,52,58,77,85,146,186],"obtain":[27],"representations":[28,53,98,116],"using":[29,79,117],"information,":[33],"such":[34],"as":[35],"audio,":[37,108],"interactions":[38],"between":[39,113],"users":[40],"and":[41,105,133,182],"songs,":[42],"or":[43],"associated":[44],"genre":[45,103,129],"metadata.":[46],"Recently,":[47],"contrastive":[48,81,119],"has":[50],"led":[51],"generalize":[55],"better":[56],"compared":[57],"traditional":[59],"supervised":[60],"methods.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65],"present":[66],"novel":[68],"approach":[69,124],"combines":[71],"types":[73],"information":[75,160],"related":[76],"cross-modal":[80],"learning,":[82],"allowing":[83],"us":[84],"learn":[86],"an":[87],"audio":[88],"feature":[89],"from":[90,100],"heterogeneous":[91],"data":[92],"simultaneously.":[93],"We":[94,121,136,150],"align":[95],"latent":[97],"obtained":[99],"playlists-track":[101],"interactions,":[102],"metadata,":[104],"tracks'":[107],"by":[109],"maximizing":[110],"agreement":[112],"these":[114,148],"modality":[115],"loss.":[120],"evaluate":[122],"our":[123,163],"in":[125,176],"three":[126,179],"tasks,":[127],"namely,":[128],"classification,":[130],"playlist":[131],"continuation":[132],"automatic":[134],"tagging.":[135],"compare":[137],"performances":[139],"with":[140],"baseline":[142,175],"audio-based":[143],"CNN":[144],"trained":[145],"predict":[147],"modalities.":[149],"also":[151],"study":[152],"importance":[154],"including":[156],"when":[161],"training":[162],"embedding":[164],"model.":[165],"The":[166],"results":[167],"suggest":[168],"proposed":[171],"method":[172],"outperforms":[173],"all":[177],"downstream":[180],"tasks":[181],"achieves":[183],"comparable":[184],"performance":[185],"state-of-the-art.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2021-04-13T00:00:00"}