{"id":"https://openalex.org/W3162583214","doi":"https://doi.org/10.1109/icassp39728.2021.9413514","title":"Multimodal Metric Learning for Tag-Based Music Retrieval","display_name":"Multimodal Metric Learning for Tag-Based Music Retrieval","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3162583214","doi":"https://doi.org/10.1109/icassp39728.2021.9413514","mag":"3162583214"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repositori.upf.edu/bitstreams/52e3eef5-965e-4d84-9777-debf5a4c5f23/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041096205","display_name":"Minz Won","orcid":"https://orcid.org/0000-0002-6921-1733"},"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":"Minz Won","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054710041","display_name":"Sergio Oramas","orcid":"https://orcid.org/0000-0002-8028-2890"},"institutions":[{"id":"https://openalex.org/I4210123445","display_name":"Pandora (United States)","ror":"https://ror.org/038m7b802","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergio Oramas","raw_affiliation_strings":["Pandora, Oakland, CA, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pandora, Oakland, CA, United States of America","institution_ids":["https://openalex.org/I4210123445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110542743","display_name":"Oriol Nieto","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123445","display_name":"Pandora (United States)","ror":"https://ror.org/038m7b802","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oriol Nieto","raw_affiliation_strings":["Pandora, Oakland, CA, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pandora, Oakland, CA, United States of America","institution_ids":["https://openalex.org/I4210123445"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015454019","display_name":"Fabien Gouyon","orcid":"https://orcid.org/0000-0001-7070-9937"},"institutions":[{"id":"https://openalex.org/I4210123445","display_name":"Pandora (United States)","ror":"https://ror.org/038m7b802","country_code":"US","type":"company","lineage":["https://openalex.org/I4210123445"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fabien Gouyon","raw_affiliation_strings":["Pandora, Oakland, CA, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pandora, Oakland, CA, United States of America","institution_ids":["https://openalex.org/I4210123445"]}]},{"author_position":"last","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":"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 Serra","raw_affiliation_strings":["Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, 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":null,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"591","last_page":"595"},"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":0.9965999722480774,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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":0.8091902732849121},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6422510147094727},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6144509315490723},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5969786643981934},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5566660165786743},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.49159082770347595},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.48588818311691284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4769093990325928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47339117527008057},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4605608880519867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4521496593952179},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4213760197162628},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16939443349838257},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0716099739074707},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07111921906471252}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091902732849121},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6422510147094727},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6144509315490723},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5969786643981934},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5566660165786743},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.49159082770347595},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.48588818311691284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4769093990325928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47339117527008057},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4605608880519867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4521496593952179},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4213760197162628},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16939443349838257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0716099739074707},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07111921906471252},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/56075","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/56075","pdf_url":"https://repositori.upf.edu/bitstreams/52e3eef5-965e-4d84-9777-debf5a4c5f23/download","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:repositori.upf.edu:10230/56075","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/56075","pdf_url":"https://repositori.upf.edu/bitstreams/52e3eef5-965e-4d84-9777-debf5a4c5f23/download","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.8799999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3402147602","display_name":null,"funder_award_id":"MDM-2015-0502","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320324211","display_name":"Ministry of Economy","ror":"https://ror.org/02fn8ac40"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3162583214.pdf","grobid_xml":"https://content.openalex.org/works/W3162583214.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1556219185","https://openalex.org/W1614298861","https://openalex.org/W1869500417","https://openalex.org/W2096733369","https://openalex.org/W2101409192","https://openalex.org/W2106053110","https://openalex.org/W2113479237","https://openalex.org/W2117154949","https://openalex.org/W2123024445","https://openalex.org/W2134584261","https://openalex.org/W2147169795","https://openalex.org/W2250539671","https://openalex.org/W2783457476","https://openalex.org/W2890267272","https://openalex.org/W2954224973","https://openalex.org/W2962968152","https://openalex.org/W2963350250","https://openalex.org/W2963389687","https://openalex.org/W2963775347","https://openalex.org/W2964121744","https://openalex.org/W2990796920","https://openalex.org/W3029858316","https://openalex.org/W3091905774","https://openalex.org/W3099206234","https://openalex.org/W3112635029","https://openalex.org/W4287635193","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6675751002","https://openalex.org/W6677328822","https://openalex.org/W6678470764","https://openalex.org/W6681737746","https://openalex.org/W6740057804","https://openalex.org/W6765174816","https://openalex.org/W6778572914","https://openalex.org/W6783596713","https://openalex.org/W6784260069"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2349784553","https://openalex.org/W2183306018","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4307058054","https://openalex.org/W2849310602","https://openalex.org/W4292238148"],"abstract_inverted_index":{"Tag-based":[0],"music":[1,13,87,95],"retrieval":[2,58,111],"is":[3],"crucial":[4],"to":[5,79],"browse":[6],"large-scale":[7],"mu-sic":[8],"libraries":[9],"efficiently.":[10],"Hence,":[11],"automatic":[12],"tagging":[14],"has":[15,25,52],"been":[16],"actively":[17],"explored,":[18],"mostly":[19],"as":[20,46],"a":[21,29,68,121],"classification":[22],"task,":[23],"which":[24],"an":[26],"inherent":[27],"limitation:":[28],"fixed":[30],"vocabulary.":[31],"On":[32],"the":[33,106,110,119,124],"other":[34,61],"hand,":[35],"metric":[36,83],"learning":[37,51,67,84],"enables":[38],"flexible":[39],"vocabularies":[40],"by":[41,65],"using":[42],"pretrained":[43],"word":[44,99],"embeddings":[45],"side":[47],"information.":[48],"Also,":[49],"met-ric":[50],"proven":[53],"its":[54],"suitability":[55],"for":[56,85],"cross-modal":[57],"tasks":[59],"in":[60],"domains":[62],"(e.g.,":[63],"text-to-image)":[64],"jointly":[66],"multimodal":[69,82],"embedding":[70],"space.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75,117],"investigate":[76],"three":[77],"ideas":[78,108],"successfully":[80],"introduce":[81],"tag-based":[86],"retrieval:":[88],"elaborate":[89],"triplet":[90],"sampling,":[91],"acoustic":[92],"and":[93,97,114,138],"cultural":[94],"information,":[96],"domain-specific":[98],"embeddings.":[100],"Our":[101],"experimental":[102],"results":[103],"show":[104],"that":[105],"proposed":[107],"enhance":[109],"system":[112],"quantitatively":[113],"qualitatively.":[115],"Furthermore,":[116],"release":[118],"MSD500:":[120],"subset":[122],"of":[123],"Million":[125],"Song":[126],"Dataset":[127],"(MSD)":[128],"containing":[129],"500":[130],"cleaned":[131],"tags,":[132],"7":[133],"manually":[134],"annotated":[135],"tag":[136],"categories,":[137],"user":[139],"taste":[140],"profiles.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
