{"id":"https://openalex.org/W4225328971","doi":"https://doi.org/10.1109/icassp43922.2022.9746131","title":"Learning Music Sequence Representation From Text Supervision","display_name":"Learning Music Sequence Representation From Text Supervision","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225328971","doi":"https://doi.org/10.1109/icassp43922.2022.9746131"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746131","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.19602","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100371626","display_name":"Tianyu Chen","orcid":"https://orcid.org/0000-0002-7109-0045"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianyu Chen","raw_affiliation_strings":["Beihang University,Bdbc,China","Sklsde, Beihang University","Bdbc, Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University,Bdbc,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sklsde, Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Bdbc, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385338","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-3803-0929"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["The Institute of Acoustics of the Chinese Academy of Sciences,China","The Institute of Acoustics of the Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"The Institute of Acoustics of the Chinese Academy of Sciences,China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"The Institute of Acoustics of the Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328838","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0001-8502-2927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Beihang University,Bdbc,China","Bdbc, Beihang University, China","Sklsde, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University,Bdbc,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Bdbc, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sklsde, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061624006","display_name":"Shaohan Huang","orcid":"https://orcid.org/0000-0003-4324-6337"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohan Huang","raw_affiliation_strings":["Microsoft Research Asia,China","Microsoft Research Asia, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia,China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086419494","display_name":"Haoyi Zhou","orcid":"https://orcid.org/0000-0002-2393-3634"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyi Zhou","raw_affiliation_strings":["Beihang University,Bdbc,China","Bdbc, Beihang University, China","Sklsde, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University,Bdbc,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Bdbc, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sklsde, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380463","display_name":"Jianxin Li","orcid":"https://orcid.org/0000-0001-5152-0055"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxin Li","raw_affiliation_strings":["Beihang University,Bdbc,China","Bdbc, Beihang University, China","Sklsde, Beihang University"],"affiliations":[{"raw_affiliation_string":"Beihang University,Bdbc,China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Bdbc, Beihang University, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Sklsde, Beihang University","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100371626"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.977,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76574307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4583","last_page":"4587"},"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":0.9991999864578247,"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":0.9955999851226807,"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":0.7715367078781128},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7322242259979248},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7290381789207458},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5417168736457825},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5041011571884155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4847838282585144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4330870509147644},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42434582114219666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715367078781128},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7322242259979248},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7290381789207458},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5417168736457825},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5041011571884155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4847838282585144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4330870509147644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42434582114219666},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746131","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:arXiv.org:2305.19602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19602","pdf_url":"https://arxiv.org/pdf/2305.19602","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.19602","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.19602","pdf_url":"https://arxiv.org/pdf/2305.19602","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4225328971.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1605494325","https://openalex.org/W2127870748","https://openalex.org/W2194775991","https://openalex.org/W2293255527","https://openalex.org/W2414894569","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2767858146","https://openalex.org/W2939574508","https://openalex.org/W2952395326","https://openalex.org/W2955142818","https://openalex.org/W2962904371","https://openalex.org/W2963091558","https://openalex.org/W2972737975","https://openalex.org/W3015523207","https://openalex.org/W3139211892","https://openalex.org/W3166396011","https://openalex.org/W3176445421","https://openalex.org/W3180663620","https://openalex.org/W3201065055","https://openalex.org/W3217385406","https://openalex.org/W4225541635","https://openalex.org/W4226181975","https://openalex.org/W4300957348","https://openalex.org/W4301077588","https://openalex.org/W4323347044","https://openalex.org/W4385245566","https://openalex.org/W6678969435","https://openalex.org/W6715395060","https://openalex.org/W6739901393","https://openalex.org/W6745878906","https://openalex.org/W6749909211","https://openalex.org/W6764574124","https://openalex.org/W6765018989","https://openalex.org/W6768465061","https://openalex.org/W6785932716","https://openalex.org/W6791353385","https://openalex.org/W6791537541","https://openalex.org/W6797810191","https://openalex.org/W6798597329","https://openalex.org/W6804489521"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2379392295","https://openalex.org/W3160965418","https://openalex.org/W613940353","https://openalex.org/W2320915480","https://openalex.org/W2362990116","https://openalex.org/W2381300099","https://openalex.org/W2795079307","https://openalex.org/W2714992399","https://openalex.org/W2793058541"],"abstract_inverted_index":{"Music":[0],"representation":[1],"learning":[2,42],"is":[3,63],"notoriously":[4],"difficult":[5],"for":[6],"its":[7],"complex":[8],"human-related":[9],"concepts":[10],"contained":[11],"in":[12],"the":[13,45,55,61,84,99],"sequence":[14],"of":[15,52,57,94],"numerical":[16],"signals.":[17],"To":[18],"excavate":[19],"better":[20],"MUsic":[21],"SEquence":[22],"Representation":[23],"from":[24,65],"labeled":[25],"audio,":[26],"we":[27],"propose":[28],"a":[29],"novel":[30],"text-supervision":[31],"pre-training":[32,87,95],"method,":[33,88],"namely":[34],"MUSER.":[35],"MUSER":[36,73],"adopts":[37],"an":[38,66],"audio-spectrum-text":[39],"tri-modal":[40],"contrastive":[41],"framework,":[43],"where":[44],"text":[46,58],"input":[47],"could":[48,74],"be":[49,75],"any":[50],"form":[51],"meta-data":[53],"with":[54,83],"help":[56],"templates":[59],"while":[60],"spectrum":[62],"derived":[64],"audio":[67],"sequence.":[68],"Our":[69],"experiments":[70],"reveal":[71],"that":[72],"more":[76],"flexibly":[77],"adapted":[78],"to":[79,97],"downstream":[80],"tasks":[81],"compared":[82],"current":[85],"data-hungry":[86],"and":[89],"it":[90],"only":[91],"requires":[92],"0.056%":[93],"data":[96],"achieve":[98],"state-of-the-art":[100],"performance.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}