{"id":"https://openalex.org/W4392909519","doi":"https://doi.org/10.1109/icassp48485.2024.10447760","title":"Joint Music and Language Attention Models for Zero-Shot Music Tagging","display_name":"Joint Music and Language Attention Models for Zero-Shot Music Tagging","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909519","doi":"https://doi.org/10.1109/icassp48485.2024.10447760"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5091528537","display_name":"Xingjian Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xingjian Du","raw_affiliation_strings":["Bytedance"],"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031063108","display_name":"Zhesong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhesong Yu","raw_affiliation_strings":["Bytedance"],"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002847471","display_name":"Jiaju Lin","orcid":"https://orcid.org/0000-0001-6988-7568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaju Lin","raw_affiliation_strings":["Bytedance"],"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100934338","display_name":"Bilei Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bilei Zhu","raw_affiliation_strings":["Bytedance"],"affiliations":[{"raw_affiliation_string":"Bytedance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuqiang Kong","raw_affiliation_strings":["The Chinese University of Hongkong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hongkong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091528537"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7077,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83525858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1126","last_page":"1130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9745000004768372,"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/joint","display_name":"Joint (building)","score":0.7554967403411865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6442421674728394},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5948870778083801},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5544379353523254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4906555712223053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38971027731895447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.366416335105896},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22809824347496033},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08911576867103577}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7554967403411865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442421674728394},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5948870778083801},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5544379353523254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4906555712223053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38971027731895447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.366416335105896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22809824347496033},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08911576867103577},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W2107430826","https://openalex.org/W2133824856","https://openalex.org/W2414894569","https://openalex.org/W2963451564","https://openalex.org/W3174770825","https://openalex.org/W3205644108","https://openalex.org/W4225323055","https://openalex.org/W4226442948","https://openalex.org/W4239318779","https://openalex.org/W4250727785","https://openalex.org/W4254415482","https://openalex.org/W4286850225","https://openalex.org/W4296405285","https://openalex.org/W4376312115","https://openalex.org/W4379251869","https://openalex.org/W4385245566","https://openalex.org/W6678969435","https://openalex.org/W6715395060","https://openalex.org/W6778572914","https://openalex.org/W6790830454","https://openalex.org/W6803752119","https://openalex.org/W6810334672","https://openalex.org/W6810510949","https://openalex.org/W6841982715","https://openalex.org/W6843286566","https://openalex.org/W6853116092","https://openalex.org/W6853393314"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Music":[0],"tagging":[1,15,22,40,57,153],"is":[2],"a":[3,37,44,69,74,78,116,150],"task":[4],"to":[5,29,52,84,103,127,130,140,169],"predict":[6],"the":[7,54,105,109,123,132,142,158,173,176],"tags":[8],"of":[9,63,155],"music":[10,14,21,39,46,56,118],"recordings.":[11],"However,":[12],"previous":[13,162,170],"research":[16],"primarily":[17],"focuses":[18],"on":[19,157,172],"close-set":[20],"tasks":[23],"which":[24],"can":[25],"not":[26],"be":[27],"generalized":[28],"new":[30],"tags.":[31],"In":[32],"this":[33],"work,":[34],"we":[35],"propose":[36,126],"zero-shot":[38,151,163],"system":[41,148],"modeled":[42,67,76],"by":[43,68,77],"joint":[45],"and":[47,73,100,111,119,137,165,175],"language":[48],"attention":[49,96],"(JMLA)":[50],"model":[51,61],"address":[53],"open-set":[55],"problem.":[58],"The":[59],"JMLA":[60,143,147],"consists":[62],"an":[64],"audio":[65,88,152],"encoder":[66,99,110],"pretrained":[70],"masked":[71],"autoencoder":[72],"decoder":[75,101,112],"Falcon7B.":[79],"We":[80,93,114,125],"introduce":[81,94],"preceiver":[82],"resampler":[83],"convert":[85,131],"arbitrary":[86],"length":[87,91],"into":[89,135],"fixed":[90],"embeddings.":[92],"dense":[95],"connections":[97],"between":[98,108],"layers":[102],"improve":[104],"information":[106],"flow":[107],"layers.":[113],"collect":[115],"large-scale":[117],"description":[120],"dataset":[121],"from":[122],"internet.":[124],"use":[128],"ChatGPT":[129],"raw":[133],"descriptions":[134,139],"formalized":[136],"diverse":[138],"train":[141],"models.":[144],"Our":[145],"proposed":[146],"achieves":[149,166],"accuracy":[154],"64.82%":[156],"GTZAN":[159],"dataset,":[160],"outperforming":[161],"systems":[164,171],"comparable":[167],"results":[168],"FMA":[174],"MagnaTagATune":[177],"datasets.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}