{"id":"https://openalex.org/W4225314222","doi":"https://doi.org/10.1109/icassp43922.2022.9746996","title":"Learning Music Audio Representations Via Weak Language Supervision","display_name":"Learning Music Audio Representations Via Weak Language Supervision","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225314222","doi":"https://doi.org/10.1109/icassp43922.2022.9746996"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746996","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5069645267","display_name":"Ilaria Manco","orcid":"https://orcid.org/0000-0001-8945-7557"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ilaria Manco","raw_affiliation_strings":["Queen Mary University of London,School of EECS,London,U.K","School of EECS, Queen Mary University of London, London, U.K","Music & Audio Machine Learning Lab, Universal Music Group, London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of EECS,London,U.K","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"School of EECS, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Music & Audio Machine Learning Lab, Universal Music Group, London, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084672392","display_name":"Emmanouil Benetos","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emmanouil Benetos","raw_affiliation_strings":["Queen Mary University of London,School of EECS,London,U.K","School of EECS, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of EECS,London,U.K","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"School of EECS, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051960947","display_name":"Elio Quinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elio Quinton","raw_affiliation_strings":["Universal Music Group,Music & Audio Machine Learning Lab,London,U.K"],"affiliations":[{"raw_affiliation_string":"Universal Music Group,Music & Audio Machine Learning Lab,London,U.K","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032485940","display_name":"Gy\u00f6rgy Fazekas","orcid":null},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gyorgy Fazekas","raw_affiliation_strings":["Queen Mary University of London,School of EECS,London,U.K","School of EECS, Queen Mary University of London, London, U.K"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,School of EECS,London,U.K","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"School of EECS, Queen Mary University of London, London, U.K","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069645267"],"corresponding_institution_ids":["https://openalex.org/I166337079"],"apc_list":null,"apc_paid":null,"fwci":2.6755,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92382751,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"456","last_page":"460"},"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":0.9959999918937683,"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":0.8417142629623413},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5244086980819702},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5111210942268372},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5077627897262573},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5035790801048279},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4683377742767334},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4625503420829773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4400368332862854},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4143083691596985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4044734537601471},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33261096477508545},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.22258612513542175},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1886879801750183}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8417142629623413},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5244086980819702},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5111210942268372},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5077627897262573},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5035790801048279},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4683377742767334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4625503420829773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4400368332862854},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4143083691596985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4044734537601471},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33261096477508545},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.22258612513542175},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1886879801750183},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746996","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746996","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/103352","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/103352","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"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":"Article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/77270","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/77270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2127870748","https://openalex.org/W2136129419","https://openalex.org/W2293255527","https://openalex.org/W2296751288","https://openalex.org/W2437181147","https://openalex.org/W2468367192","https://openalex.org/W2580221632","https://openalex.org/W2592168896","https://openalex.org/W2604959036","https://openalex.org/W2606176153","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2950060770","https://openalex.org/W2963707325","https://openalex.org/W2966715458","https://openalex.org/W3005680577","https://openalex.org/W3015523207","https://openalex.org/W3015949486","https://openalex.org/W3029858316","https://openalex.org/W3090449556","https://openalex.org/W3090634605","https://openalex.org/W3097217077","https://openalex.org/W3105202226","https://openalex.org/W3139211892","https://openalex.org/W3143852976","https://openalex.org/W3160719641","https://openalex.org/W3163035491","https://openalex.org/W3174942519","https://openalex.org/W3180663620","https://openalex.org/W4287757056","https://openalex.org/W4288089799","https://openalex.org/W4297808394","https://openalex.org/W6678969435","https://openalex.org/W6697263322","https://openalex.org/W6719713019","https://openalex.org/W6732646663","https://openalex.org/W6736327223","https://openalex.org/W6736723571","https://openalex.org/W6745586488","https://openalex.org/W6755207826","https://openalex.org/W6763945542","https://openalex.org/W6766904570","https://openalex.org/W6769627184","https://openalex.org/W6774314701","https://openalex.org/W6776721752","https://openalex.org/W6778572914","https://openalex.org/W6779191341","https://openalex.org/W6784028902","https://openalex.org/W6791537541","https://openalex.org/W6797624625","https://openalex.org/W6798597329"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926","https://openalex.org/W2157165686","https://openalex.org/W2371215329","https://openalex.org/W1975359510"],"abstract_inverted_index":{"Audio":[0],"representations":[1,146,187],"for":[2,80],"music":[3,68,81,127],"information":[4],"retrieval":[5],"are":[6,189],"typically":[7],"learned":[8],"via":[9,87],"supervised":[10],"learning":[11],"in":[12,97,197],"a":[13,33,77,88,124],"task-specific":[14],"fashion.":[15],"Although":[16],"effective":[17],"at":[18],"producing":[19],"state-of-the-art":[20],"results,":[21],"this":[22,43,73],"scheme":[23],"lacks":[24],"flexibility":[25],"with":[26,153,191],"respect":[27],"to":[28,55,65,123,185],"the":[29,47,61,98,106,111,117,121,135,142,149,198],"range":[30],"of":[31,49,90,100,110,120,126,137,144],"applications":[32],"model":[34,122],"can":[35],"have":[36],"and":[37,82,130,157,172,193],"requires":[38],"extensively":[39],"annotated":[40],"datasets.":[41],"In":[42],"work,":[44],"we":[45,75,115],"pose":[46],"question":[48],"whether":[50],"it":[51],"may":[52],"be":[53],"possible":[54],"exploit":[56],"weakly":[57],"aligned":[58],"text":[59],"as":[60],"only":[62],"supervisory":[63],"signal":[64],"learn":[66,186],"general-purpose":[67],"audio":[69,118,128,145,151],"representations.":[70],"To":[71],"address":[72],"question,":[74],"design":[76],"multimodal":[78],"architecture":[79],"language":[83,103],"pre-training":[84,161],"(MuLaP)":[85],"optimised":[86],"set":[89,125],"proxy":[91],"tasks.":[92,132],"Weak":[93],"supervision":[94],"is":[95],"provided":[96],"form":[99],"noisy":[101],"natural":[102],"descriptions":[104],"conveying":[105],"overall":[107],"musical":[108],"content":[109],"track.":[112],"After":[113],"pre-training,":[114],"transfer":[116],"backbone":[119,152],"classification":[129],"regression":[131],"We":[133],"demonstrate":[134],"usefulness":[136],"our":[138,160],"approach":[139],"by":[140,148],"comparing":[141],"performance":[143],"produced":[147],"same":[150],"different":[154],"training":[155],"strategies":[156],"show":[158],"that":[159,179,188],"method":[162],"consistently":[163],"achieves":[164],"comparable":[165],"or":[166],"higher":[167],"scores":[168],"on":[169],"all":[170],"tasks":[171],"datasets":[173],"considered.":[174],"Our":[175],"experiments":[176],"also":[177],"confirm":[178],"MuLaP":[180],"effectively":[181],"leverages":[182],"audio-caption":[183],"pairs":[184],"competitive":[190],"audio-only":[192],"cross-modal":[194],"self-supervised":[195],"methods":[196],"literature.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}