{"id":"https://openalex.org/W4372259826","doi":"https://doi.org/10.1109/icassp49357.2023.10094628","title":"Multitrack Music Transformer","display_name":"Multitrack Music Transformer","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259826","doi":"https://doi.org/10.1109/icassp49357.2023.10094628"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04766516/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028026494","display_name":"Hao\u2010Wen Dong","orcid":"https://orcid.org/0000-0002-1020-0001"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao-Wen Dong","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451980","display_name":"Ke Chen","orcid":"https://orcid.org/0000-0001-8357-3741"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Chen","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042278809","display_name":"Shlomo Dubnov","orcid":"https://orcid.org/0000-0003-0222-1125"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Dubnov","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021827617","display_name":"Julian McAuley","orcid":"https://orcid.org/0000-0003-0955-7588"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julian McAuley","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017455302","display_name":"Taylor Berg-Kirkpatrick","orcid":"https://orcid.org/0000-0002-1283-4075"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taylor Berg-Kirkpatrick","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028026494"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":7.6364,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9820711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9997000098228455,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7353143692016602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6797397136688232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5152104496955872},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5055172443389893},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4884142279624939},{"id":"https://openalex.org/keywords/improvisation","display_name":"Improvisation","score":0.421719491481781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33677908778190613},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15747958421707153},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1338963508605957},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13112446665763855},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10393062233924866}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7353143692016602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797397136688232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5152104496955872},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5055172443389893},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4884142279624939},{"id":"https://openalex.org/C125468537","wikidata":"https://www.wikidata.org/wiki/Q214961","display_name":"Improvisation","level":2,"score":0.421719491481781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33677908778190613},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15747958421707153},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1338963508605957},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13112446665763855},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10393062233924866},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04766516v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766516","pdf_url":"https://hal.science/hal-04766516/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, France. pp.1-5, &#x27E8;10.1109/ICASSP49357.2023.10094628&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04766516v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04766516","pdf_url":"https://hal.science/hal-04766516/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2023, Rhodes Island, France. pp.1-5, &#x27E8;10.1109/ICASSP49357.2023.10094628&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3396663625","display_name":"Raising co-creativity in cyber-human musicianship","funder_award_id":"883313","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8051717526","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4372259826.pdf","grobid_xml":"https://content.openalex.org/works/W4372259826.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W2559110679","https://openalex.org/W2772474126","https://openalex.org/W2775473773","https://openalex.org/W2805697608","https://openalex.org/W2919624000","https://openalex.org/W2963045354","https://openalex.org/W2981646816","https://openalex.org/W2991108091","https://openalex.org/W3003673875","https://openalex.org/W3047325651","https://openalex.org/W3047386385","https://openalex.org/W3047571292","https://openalex.org/W3049272330","https://openalex.org/W3099378280","https://openalex.org/W3108047681","https://openalex.org/W3129917041","https://openalex.org/W3173187964","https://openalex.org/W3175663427","https://openalex.org/W3182909996","https://openalex.org/W3213549365","https://openalex.org/W4221148975","https://openalex.org/W4286859130","https://openalex.org/W4292779060","https://openalex.org/W4302076919","https://openalex.org/W4372260493","https://openalex.org/W4377719641","https://openalex.org/W4385245566","https://openalex.org/W4394640856","https://openalex.org/W6730424109","https://openalex.org/W6739901393","https://openalex.org/W6746528227","https://openalex.org/W6748148878","https://openalex.org/W6750630487","https://openalex.org/W6751598888","https://openalex.org/W6760601182","https://openalex.org/W6765759998","https://openalex.org/W6769848495","https://openalex.org/W6773252663","https://openalex.org/W6778883912","https://openalex.org/W6781423933","https://openalex.org/W6781484447","https://openalex.org/W6781678156","https://openalex.org/W6781972552","https://openalex.org/W6785529287","https://openalex.org/W6798288246","https://openalex.org/W6800194770","https://openalex.org/W6803953198","https://openalex.org/W6840122634"],"related_works":["https://openalex.org/W2052817658","https://openalex.org/W2129561254","https://openalex.org/W2146959957","https://openalex.org/W3208261218","https://openalex.org/W4283687250","https://openalex.org/W4281385181","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Existing":[0],"approaches":[1],"for":[2,105,121],"generating":[3],"multitrack":[4,52],"music":[5,23,53],"with":[6,77,140],"transformer":[7],"models":[8,86],"have":[9],"been":[10],"limited":[11],"in":[12,81,87],"terms":[13],"of":[14,17,21,36,60],"the":[15,19,22,33,37,102,128,141,153],"number":[16],"instruments,":[18],"length":[20],"segments":[24],"and":[25,96,125,144],"slow":[26],"inference.":[27],"This":[28],"is":[29],"partly":[30],"due":[31],"to":[32,133,145],"memory":[34,97],"requirements":[35],"lengthy":[38],"input":[39],"sequences":[40],"necessitated":[41],"by":[42],"existing":[43],"representations.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,116],"propose":[49,117],"a":[50,57,64,88,118,137],"new":[51,119],"representation":[54],"that":[55,127,135,147],"allows":[56],"diverse":[58],"set":[59],"instruments":[61],"while":[62,92],"keeping":[63],"short":[65],"sequence":[66],"length.":[67],"Our":[68],"proposed":[69,85],"Multitrack":[70],"Music":[71],"Transformer":[72],"(MMT)":[73],"achieves":[74],"comparable":[75],"performance":[76],"state-of-the-art":[78],"systems,":[79],"landing":[80],"between":[82],"two":[83],"recently":[84],"subjective":[89],"listening":[90],"test,":[91],"achieving":[93],"substantial":[94],"speedups":[95],"reductions":[98],"over":[99],"both,":[100],"making":[101],"method":[103],"attractive":[104],"real":[106,111],"time":[107,112],"improvisation":[108],"or":[109],"near":[110],"creative":[113],"applications.":[114],"Further,":[115],"measure":[120],"analyzing":[122],"musical":[123],"self-attention":[124],"show":[126],"trained":[129],"model":[130],"attends":[131],"more":[132],"notes":[134,146],"form":[136],"consonant":[138],"interval":[139],"current":[142,154],"note":[143],"are":[148],"4N":[149],"beats":[150],"away":[151],"from":[152],"step.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
