{"id":"https://openalex.org/W3015474055","doi":"https://doi.org/10.1109/icassp40776.2020.9054352","title":"Audio-Based Auto-Tagging With Contextual Tags for Music","display_name":"Audio-Based Auto-Tagging With Contextual Tags for Music","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015474055","doi":"https://doi.org/10.1109/icassp40776.2020.9054352","mag":"3015474055"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054352","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/A5033550190","display_name":"Karim M. Ibrahim","orcid":"https://orcid.org/0000-0003-3315-9539"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Karim M. Ibrahim","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073972555","display_name":"Jimena Royo-Letelier","orcid":null},"institutions":[{"id":"https://openalex.org/I4403386605","display_name":"PRX Research","ror":"https://ror.org/03f0sw771","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403386605"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jimena Royo-Letelier","raw_affiliation_strings":["Deezer Research & Development"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deezer Research & Development","institution_ids":["https://openalex.org/I4403386605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077407955","display_name":"Elena V. Epure","orcid":"https://orcid.org/0000-0002-6930-9482"},"institutions":[{"id":"https://openalex.org/I4403386605","display_name":"PRX Research","ror":"https://ror.org/03f0sw771","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403386605"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Elena V. Epure","raw_affiliation_strings":["Deezer Research & Development"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deezer Research & Development","institution_ids":["https://openalex.org/I4403386605"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4648,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90547264,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"20"},"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":0.9966999888420105,"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":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.8501309156417847},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5212852954864502},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5074188113212585},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4950818121433258},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4792761504650116},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4484519958496094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4405536353588104},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4321478605270386},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.42860332131385803},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4244147837162018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3658542037010193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3577702045440674},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33981412649154663},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3313808739185333},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.22569146752357483}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8501309156417847},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5212852954864502},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5074188113212585},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4950818121433258},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4792761504650116},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4484519958496094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4405536353588104},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4321478605270386},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.42860332131385803},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4244147837162018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3658542037010193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3577702045440674},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33981412649154663},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3313808739185333},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.22569146752357483},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054352","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","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W65280498","https://openalex.org/W80471776","https://openalex.org/W1532398148","https://openalex.org/W1995797952","https://openalex.org/W2025335430","https://openalex.org/W2025605741","https://openalex.org/W2039218094","https://openalex.org/W2049229728","https://openalex.org/W2115568835","https://openalex.org/W2146241755","https://openalex.org/W2286124384","https://openalex.org/W2332720221","https://openalex.org/W2414894569","https://openalex.org/W2507319753","https://openalex.org/W2592890084","https://openalex.org/W2618371569","https://openalex.org/W2766658708","https://openalex.org/W2767858146","https://openalex.org/W2774180115","https://openalex.org/W2774685635","https://openalex.org/W2804930930","https://openalex.org/W2889271120","https://openalex.org/W2892896937","https://openalex.org/W2938834426","https://openalex.org/W2962813390","https://openalex.org/W2963351448","https://openalex.org/W4232836321","https://openalex.org/W6715395060","https://openalex.org/W6751665580"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218"],"abstract_inverted_index":{"Music":[0],"listening":[1],"context":[2,27,61,131],"such":[3],"as":[4,57],"location":[5],"or":[6],"activity":[7],"has":[8],"been":[9],"shown":[10],"to":[11,33,39,49,109,120],"greatly":[12],"influence":[13],"the":[14,23,86,95,123],"users'":[15],"musical":[16],"tastes.":[17],"In":[18],"this":[19],"work,":[20],"we":[21,44,65,80,112],"study":[22],"relationship":[24],"between":[25],"user":[26,40],"and":[28,67,97,128],"audio":[29,91],"content":[30],"in":[31,125],"order":[32],"enable":[34],"context-aware":[35],"music":[36],"recommendation":[37],"agnostic":[38],"data.":[41],"For":[42],"that,":[43],"propose":[45,113],"a":[46,58,69,114],"semi-automatic":[47],"procedure":[48],"collect":[50],"track":[51],"sets":[52],"which":[53],"leverages":[54],"playlist":[55],"titles":[56],"proxy":[59],"for":[60,122],"labelling.":[62],"Using":[63],"this,":[64],"create":[66],"release":[68],"dataset":[70,88],"of":[71,99],"~50k":[72],"tracks":[73],"labelled":[74],"with":[75],"15":[76],"different":[77],"contexts.":[78],"Then,":[79],"present":[81],"benchmark":[82],"classification":[83],"results":[84],"on":[85],"created":[87],"using":[89],"an":[90],"auto-tagging":[92],"model.":[93],"As":[94],"training":[96],"evaluation":[98],"these":[100],"models":[101],"are":[102],"impacted":[103],"by":[104],"missing":[105,126],"negative":[106],"labels":[107,127],"due":[108],"incomplete":[110],"annotations,":[111],"sample-level":[115],"weighted":[116],"cross":[117],"entropy":[118],"loss":[119],"account":[121],"confidence":[124],"show":[129],"improved":[130],"prediction":[132],"results.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
