{"id":"https://openalex.org/W4392904213","doi":"https://doi.org/10.1109/icassp48485.2024.10448314","title":"A Foundation Model for Music Informatics","display_name":"A Foundation Model for Music Informatics","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904213","doi":"https://doi.org/10.1109/icassp48485.2024.10448314"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448314","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/A5041096205","display_name":"Minz Won","orcid":"https://orcid.org/0000-0002-6921-1733"},"institutions":[{"id":"https://openalex.org/I4210139888","display_name":"Good Samaritan Hospital","ror":"https://ror.org/03zms7281","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210139888"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minz Won","raw_affiliation_strings":["ByteDance,SAMI,San Jose,CA,USA","SAMI, ByteDance, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance,SAMI,San Jose,CA,USA","institution_ids":["https://openalex.org/I4210139888"]},{"raw_affiliation_string":"SAMI, ByteDance, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I4210139888","display_name":"Good Samaritan Hospital","ror":"https://ror.org/03zms7281","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210139888"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["ByteDance,SAMI,San Jose,CA,USA","SAMI, ByteDance, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance,SAMI,San Jose,CA,USA","institution_ids":["https://openalex.org/I4210139888"]},{"raw_affiliation_string":"SAMI, ByteDance, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085310066","display_name":"Manh Duc Le","orcid":"https://orcid.org/0000-0003-3012-6053"},"institutions":[{"id":"https://openalex.org/I4210139888","display_name":"Good Samaritan Hospital","ror":"https://ror.org/03zms7281","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210139888"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["ByteDance,SAMI,San Jose,CA,USA","SAMI, ByteDance, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"ByteDance,SAMI,San Jose,CA,USA","institution_ids":["https://openalex.org/I4210139888"]},{"raw_affiliation_string":"SAMI, ByteDance, San Jose, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041096205"],"corresponding_institution_ids":["https://openalex.org/I4210139888"],"apc_list":null,"apc_paid":null,"fwci":5.2079,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.96213296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1226","last_page":"1230"},"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":0.9896000027656555,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9666000008583069,"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":0.813084065914154},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.621208131313324},{"id":"https://openalex.org/keywords/informatics","display_name":"Informatics","score":0.5343000292778015},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5334759950637817},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.502094030380249},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4781816303730011},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4569781422615051},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.45588573813438416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44979265332221985},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.42387300729751587},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4200781583786011},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35833311080932617},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10146573185920715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.813084065914154},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.621208131313324},{"id":"https://openalex.org/C191630685","wikidata":"https://www.wikidata.org/wiki/Q4027615","display_name":"Informatics","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5334759950637817},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.502094030380249},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4781816303730011},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4569781422615051},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.45588573813438416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44979265332221985},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42387300729751587},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4200781583786011},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35833311080932617},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10146573185920715},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448314","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448314","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2293255527","https://openalex.org/W2572771584","https://openalex.org/W2901314291","https://openalex.org/W3036601975","https://openalex.org/W3081168214","https://openalex.org/W3094502228","https://openalex.org/W3195577433","https://openalex.org/W3209059054","https://openalex.org/W4214612132","https://openalex.org/W4224918587","https://openalex.org/W4224944643","https://openalex.org/W4225434581","https://openalex.org/W4281758439","https://openalex.org/W4287802874","https://openalex.org/W4292779060","https://openalex.org/W4307323391","https://openalex.org/W4372259862","https://openalex.org/W4379251869","https://openalex.org/W4386763510","https://openalex.org/W6631190155","https://openalex.org/W6641088196","https://openalex.org/W6678969435","https://openalex.org/W6714030504","https://openalex.org/W6732646663","https://openalex.org/W6736327223","https://openalex.org/W6753689128","https://openalex.org/W6755207826","https://openalex.org/W6756801033","https://openalex.org/W6765005523","https://openalex.org/W6770646036","https://openalex.org/W6774314701","https://openalex.org/W6778572914","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6782211628","https://openalex.org/W6784333009","https://openalex.org/W6784614252","https://openalex.org/W6791353385","https://openalex.org/W6791537541","https://openalex.org/W6798597329","https://openalex.org/W6803752119","https://openalex.org/W6810673746","https://openalex.org/W6838322825","https://openalex.org/W6846414411","https://openalex.org/W6846470732"],"related_works":["https://openalex.org/W1501776718","https://openalex.org/W2615136228","https://openalex.org/W2389214306","https://openalex.org/W657108774","https://openalex.org/W4235240664","https://openalex.org/W2390192952","https://openalex.org/W2965083567","https://openalex.org/W2480620430","https://openalex.org/W2373296418","https://openalex.org/W1838576100"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"investigates":[2],"foundation":[3,33,71,143],"models":[4,72,87,116,144],"tailored":[5],"for":[6,137],"music":[7,74,93,131],"informatics,":[8],"a":[9,77,97],"domain":[10],"currently":[11],"challenged":[12],"by":[13,60],"the":[14,56,68,83,125,135,146],"scarcity":[15],"of":[16,70,85,127,151],"labeled":[17],"data":[18],"and":[19,48,102,133,141,160],"generalization":[20],"issues.":[21],"To":[22],"this":[23],"end,":[24],"we":[25,81],"conduct":[26],"an":[27],"in-depth":[28],"comparative":[29],"study":[30],"among":[31],"various":[32],"model":[34,41,49,110,153],"variants,":[35],"examining":[36],"key":[37,119],"determinants":[38],"such":[39],"as":[40],"architectures,":[42],"tokenization":[43],"methods,":[44],"temporal":[45],"resolution,":[46],"data,":[47],"scalability.":[50],"research":[52],"aims":[53],"to":[54,67,124,157],"bridge":[55],"existing":[57,115],"knowledge":[58],"gap":[59],"elucidating":[61],"how":[62],"these":[63,86],"individual":[64],"factors":[65],"contribute":[66,123],"success":[69],"in":[73,92,117,130,145],"informatics.":[75],"Employing":[76],"careful":[78],"evaluation":[79],"frame-work,":[80],"assess":[82],"performance":[84],"across":[88],"diverse":[89],"downstream":[90],"tasks":[91],"information":[94],"retrieval,":[95],"with":[96],"particular":[98],"focus":[99],"on":[100],"frame-level":[101],"sequence-level":[103],"classification.":[104],"Our":[105],"results":[106],"reveal":[107],"that":[108],"our":[109,152],"demonstrates":[111],"robust":[112],"performance,":[113],"surpassing":[114],"specific":[118],"metrics.":[120],"These":[121],"findings":[122],"understanding":[126],"self-supervised":[128],"learning":[129],"informatics":[132],"pave":[134],"way":[136],"developing":[138],"more":[139],"effective":[140],"versatile":[142],"field.":[147],"A":[148],"pretrained":[149],"version":[150],"is":[154],"publicly":[155],"available":[156],"foster":[158],"reproducibility":[159],"future":[161],"research.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-02-26T06:29:33.603293","created_date":"2025-10-10T00:00:00"}
