{"id":"https://openalex.org/W4293518176","doi":"https://doi.org/10.1109/icme52920.2022.9859799","title":"Towards Proper Contrastive Self-Supervised Learning Strategies for Music Audio Representation","display_name":"Towards Proper Contrastive Self-Supervised Learning Strategies for Music Audio Representation","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4293518176","doi":"https://doi.org/10.1109/icme52920.2022.9859799"},"language":"en","primary_location":{"id":"doi:10.1109/icme52920.2022.9859799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859799","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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/A5063581325","display_name":"Jeong Dan Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jeong Choi","raw_affiliation_strings":["NAVER Corp"],"affiliations":[{"raw_affiliation_string":"NAVER Corp","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041231693","display_name":"Seongwon Jang","orcid":"https://orcid.org/0000-0002-9651-8167"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seongwon Jang","raw_affiliation_strings":["NCSOFT,Knowledge AI Lab","Tmap Mobility Co., Ltd","Knowledge AI Lab., NCSOFT"],"affiliations":[{"raw_affiliation_string":"NCSOFT,Knowledge AI Lab","institution_ids":[]},{"raw_affiliation_string":"Tmap Mobility Co., Ltd","institution_ids":[]},{"raw_affiliation_string":"Knowledge AI Lab., NCSOFT","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044711814","display_name":"Hyunsouk Cho","orcid":"https://orcid.org/0000-0002-9134-1921"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunsouk Cho","raw_affiliation_strings":["Ajou University"],"affiliations":[{"raw_affiliation_string":"Ajou University","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047186923","display_name":"Sehee Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sehee Chung","raw_affiliation_strings":["NCSOFT,Knowledge AI Lab","Knowledge AI Lab., NCSOFT"],"affiliations":[{"raw_affiliation_string":"NCSOFT,Knowledge AI Lab","institution_ids":[]},{"raw_affiliation_string":"Knowledge AI Lab., NCSOFT","institution_ids":["https://openalex.org/I4210135449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063581325"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":0.6129,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.65181675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9886999726295471,"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":0.9761000275611877,"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":0.7842230200767517},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6243894696235657},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5743061304092407},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5647631883621216},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5598717331886292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.529583215713501},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5098208785057068},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.49184489250183105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39906105399131775},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3837626278400421},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11682000756263733},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.08772855997085571}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7842230200767517},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6243894696235657},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5743061304092407},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5647631883621216},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5598717331886292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529583215713501},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5098208785057068},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.49184489250183105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39906105399131775},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3837626278400421},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11682000756263733},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.08772855997085571},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme52920.2022.9859799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme52920.2022.9859799","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"2022 IEEE International Conference on Multimedia and Expo (ICME)","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":"2022 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1531663008","https://openalex.org/W1915070853","https://openalex.org/W2116206254","https://openalex.org/W2152790380","https://openalex.org/W2163922914","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2398055577","https://openalex.org/W2558661413","https://openalex.org/W2580221632","https://openalex.org/W2592168896","https://openalex.org/W2605350416","https://openalex.org/W2767754137","https://openalex.org/W2887997457","https://openalex.org/W2896457183","https://openalex.org/W2935542736","https://openalex.org/W2962739339","https://openalex.org/W2962960500","https://openalex.org/W2963451564","https://openalex.org/W2963571336","https://openalex.org/W2964265892","https://openalex.org/W2964274466","https://openalex.org/W2972737975","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W3005680577","https://openalex.org/W3015213852","https://openalex.org/W3015470225","https://openalex.org/W3015829441","https://openalex.org/W3015847222","https://openalex.org/W3016011332","https://openalex.org/W3034445277","https://openalex.org/W3034781633","https://openalex.org/W3036601975","https://openalex.org/W3093475354","https://openalex.org/W3105114834","https://openalex.org/W3105202226","https://openalex.org/W3139211892","https://openalex.org/W3144810982","https://openalex.org/W3148040514","https://openalex.org/W3162391496","https://openalex.org/W4286850225","https://openalex.org/W4294170691","https://openalex.org/W4297808394","https://openalex.org/W6631829595","https://openalex.org/W6682691769","https://openalex.org/W6682948231","https://openalex.org/W6712240000","https://openalex.org/W6732646663","https://openalex.org/W6754278344","https://openalex.org/W6755207826","https://openalex.org/W6768465061","https://openalex.org/W6769196770","https://openalex.org/W6774314701","https://openalex.org/W6779879114","https://openalex.org/W6780218876","https://openalex.org/W6786472852","https://openalex.org/W6791537541","https://openalex.org/W6803752119","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W2309093070","https://openalex.org/W3118638206","https://openalex.org/W2794946013","https://openalex.org/W1983629434","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2242773987"],"abstract_inverted_index":{"The":[0],"common":[1],"research":[2],"goal":[3],"of":[4,52,67,88,94,105],"self-supervised":[5,33],"learning":[6,34,69],"is":[7],"to":[8,62],"extract":[9],"a":[10,81],"general":[11],"representation":[12,28],"which":[13],"an":[14],"arbitrary":[15],"downstream":[16],"task":[17],"would":[18],"benefit":[19],"from.":[20],"In":[21],"this":[22],"work,":[23],"we":[24],"investigate":[25],"music":[26,44,54,89],"audio":[27],"learned":[29],"from":[30],"different":[31,50,72],"contrastive":[32,68],"schemes":[35],"and":[36],"empirically":[37],"evaluate":[38],"the":[39,53,60,64,85,95],"embedded":[40],"vectors":[41],"on":[42],"various":[43],"information":[45,83],"retrieval":[46],"(MIR)":[47],"tasks":[48],"where":[49],"levels":[51],"perception":[55],"are":[56],"concerned.":[57],"We":[58,75],"analyze":[59],"results":[61],"discuss":[63],"proper":[65],"direction":[66],"strategies":[70,97],"for":[71],"MIR":[73],"tasks.":[74],"show":[76],"that":[77],"these":[78],"representations":[79],"convey":[80],"comprehensive":[82],"about":[84],"auditory":[86],"characteristics":[87],"in":[90,102],"general,":[91],"although":[92],"each":[93],"self-supervision":[96],"has":[98],"its":[99],"own":[100],"effectiveness":[101],"certain":[103],"aspect":[104],"information.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}