{"id":"https://openalex.org/W3176689276","doi":"https://doi.org/10.1109/cbmi50038.2021.9461913","title":"Loss Function Approaches for Multi-label Music Tagging","display_name":"Loss Function Approaches for Multi-label Music Tagging","publication_year":2021,"publication_date":"2021-06-24","ids":{"openalex":"https://openalex.org/W3176689276","doi":"https://doi.org/10.1109/cbmi50038.2021.9461913","mag":"3176689276"},"language":"en","primary_location":{"id":"doi:10.1109/cbmi50038.2021.9461913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi50038.2021.9461913","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Content-Based Multimedia Indexing (CBMI)","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/A5002223602","display_name":"Dillon Knox","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dillon Knox","raw_affiliation_strings":["USC,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Electrical Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060475014","display_name":"Timothy Greer","orcid":"https://orcid.org/0000-0002-0833-8060"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Timothy Greer","raw_affiliation_strings":["USC,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Computer Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101544486","display_name":"Benjamin Ma","orcid":"https://orcid.org/0000-0003-4290-0114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Ma","raw_affiliation_strings":["USC,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Computer Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042069207","display_name":"Emily Kuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emily Kuo","raw_affiliation_strings":["USC,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Electrical Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna Somandepalli","raw_affiliation_strings":["USC,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Electrical Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103555640","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["USC,Department of Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4633,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60922541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9901000261306763,"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":0.9815000295639038,"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":0.7983295917510986},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6768700480461121},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6262074112892151},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6049615144729614},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.577102780342102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5550478100776672},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4597715139389038},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44837531447410583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4301464259624481},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4258453845977783},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.24162042140960693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7983295917510986},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6768700480461121},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6262074112892151},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6049615144729614},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.577102780342102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5550478100776672},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4597715139389038},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44837531447410583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4301464259624481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4258453845977783},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.24162042140960693},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cbmi50038.2021.9461913","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi50038.2021.9461913","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1556219185","https://openalex.org/W2339172597","https://openalex.org/W2753211788","https://openalex.org/W2765407302","https://openalex.org/W2767106145","https://openalex.org/W2950060770","https://openalex.org/W2963351448","https://openalex.org/W2963399829","https://openalex.org/W2963691377","https://openalex.org/W2964121744","https://openalex.org/W2982862350","https://openalex.org/W2986663693","https://openalex.org/W2988742732","https://openalex.org/W3015289235","https://openalex.org/W3029858316","https://openalex.org/W3043585785","https://openalex.org/W3045349544","https://openalex.org/W3090085715","https://openalex.org/W3090634605","https://openalex.org/W3091687589","https://openalex.org/W3095707208","https://openalex.org/W3101643310","https://openalex.org/W3173505822","https://openalex.org/W6631190155","https://openalex.org/W6745136726","https://openalex.org/W6763945542","https://openalex.org/W6769198072","https://openalex.org/W6770069182","https://openalex.org/W6778572914","https://openalex.org/W6780755725","https://openalex.org/W6784028902"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W3135448569"],"abstract_inverted_index":{"Given":[0],"the":[1,47,68,69,81,93,117,123,126,141],"ever-increasing":[2],"volume":[3],"of":[4,49,125,143],"music":[5,20,137],"created":[6],"and":[7,53,113],"released":[8],"every":[9],"day,":[10],"it":[11],"has":[12],"never":[13],"been":[14],"more":[15],"important":[16],"to":[17],"study":[18],"automatic":[19],"tagging.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,88],"present":[26],"an":[27,72],"ensemble-based":[28],"convolutional":[29],"neural":[30],"network":[31],"(CNN)":[32],"model":[33,110],"trained":[34,102],"using":[35,61,103],"various":[36],"loss":[37,51,63,127],"functions":[38,52],"for":[39,131],"tagging":[40],"musical":[41],"genres":[42],"from":[43,91],"audio.":[44],"We":[45,120],"investigate":[46],"effect":[48],"different":[50],"resampling":[54],"strategies":[55],"on":[56,67,96,116,133],"prediction":[57],"performance,":[58],"finding":[59],"that":[60,122],"focal":[62],"improves":[64],"overall":[65],"performance":[66,111,115],"MTG-Jamendo":[70],"dataset:":[71],"imbalanced,":[73],"multi-label":[74],"dataset":[75],"with":[76],"over":[77],"18,000":[78],"songs":[79],"in":[80,108,136,140],"public":[82],"domain,":[83],"containing":[84],"57":[85],"labels.":[86],"Additionally,":[87],"report":[89],"results":[90,107],"varying":[92],"receptive":[94],"field":[95],"our":[97],"base":[98],"classifier-a":[99],"CNN-based":[100],"architecture":[101],"Mel":[104],"spectrograms-which":[105],"also":[106],"a":[109],"boost":[112],"state-of-the-art":[114],"Jamendo":[118],"dataset.":[119],"conclude":[121],"choice":[124],"function":[128],"is":[129],"paramount":[130],"improving":[132],"existing":[134],"methods":[135],"tagging,":[138],"particularly":[139],"presence":[142],"class":[144],"imbalance.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}