{"id":"https://openalex.org/W4372260308","doi":"https://doi.org/10.1109/icassp49357.2023.10096688","title":"Multitrack Music Transcription with a Time-Frequency Perceiver","display_name":"Multitrack Music Transcription with a Time-Frequency Perceiver","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260308","doi":"https://doi.org/10.1109/icassp49357.2023.10096688"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096688","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":"conference-paper","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/A5070642261","display_name":"Wei-Tsung Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei -Tsung Lu","raw_affiliation_strings":["SAMI,ByteDance, Mountain View,CA,USA","ByteDance, Mountain View, SAMI, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance, Mountain View,CA,USA","institution_ids":[]},{"raw_affiliation_string":"ByteDance, Mountain View, SAMI, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065288078","display_name":"Ju-Chiang Wang","orcid":"https://orcid.org/0009-0002-8265-4229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ju-Chiang Wang","raw_affiliation_strings":["SAMI,ByteDance, Mountain View,CA,USA","ByteDance, Mountain View, SAMI, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance, Mountain View,CA,USA","institution_ids":[]},{"raw_affiliation_string":"ByteDance, Mountain View, SAMI, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun -Ning Hung","raw_affiliation_strings":["SAMI,ByteDance, Mountain View,CA,USA","ByteDance, Mountain View, SAMI, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SAMI,ByteDance, Mountain View,CA,USA","institution_ids":[]},{"raw_affiliation_string":"ByteDance, Mountain View, SAMI, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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":0.9998000264167786,"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":0.9983999729156494,"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":0.7557282447814941},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.640733540058136},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6102738380432129},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6048281788825989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5536436438560486},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5029670596122742},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.47564053535461426},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4560115933418274},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.41126927733421326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3954606354236603},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07349461317062378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557282447814941},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.640733540058136},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6102738380432129},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6048281788825989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5536436438560486},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5029670596122742},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.47564053535461426},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4560115933418274},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.41126927733421326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3954606354236603},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07349461317062378},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096688","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W2302255633","https://openalex.org/W2475687244","https://openalex.org/W2669032454","https://openalex.org/W2796571515","https://openalex.org/W2899260162","https://openalex.org/W2902076983","https://openalex.org/W2903342162","https://openalex.org/W2908510526","https://openalex.org/W2932319787","https://openalex.org/W2950547518","https://openalex.org/W2986673441","https://openalex.org/W2998490864","https://openalex.org/W3095303521","https://openalex.org/W3097777922","https://openalex.org/W3122606659","https://openalex.org/W3133205200","https://openalex.org/W3160649916","https://openalex.org/W3169064633","https://openalex.org/W3206146520","https://openalex.org/W3207444892","https://openalex.org/W4221159539","https://openalex.org/W4224918587","https://openalex.org/W4224944643","https://openalex.org/W4226266814","https://openalex.org/W4283360488","https://openalex.org/W4286850225","https://openalex.org/W4286980120","https://openalex.org/W4293775315","https://openalex.org/W4295312788","https://openalex.org/W4322615164","https://openalex.org/W6640212811","https://openalex.org/W6698183232","https://openalex.org/W6745851314","https://openalex.org/W6755182157","https://openalex.org/W6756010389","https://openalex.org/W6756341328","https://openalex.org/W6756884195","https://openalex.org/W6757817989","https://openalex.org/W6766978945","https://openalex.org/W6788796638","https://openalex.org/W6790830454","https://openalex.org/W6791383405","https://openalex.org/W6801426729","https://openalex.org/W6803003856","https://openalex.org/W6803088475","https://openalex.org/W6803752119","https://openalex.org/W6810079335","https://openalex.org/W6811157148","https://openalex.org/W6839196917"],"related_works":["https://openalex.org/W2389214306","https://openalex.org/W2965083567","https://openalex.org/W4235240664","https://openalex.org/W1838576100","https://openalex.org/W2757182831","https://openalex.org/W2095886385","https://openalex.org/W2089704382","https://openalex.org/W1983399550","https://openalex.org/W97075385","https://openalex.org/W2357523926"],"abstract_inverted_index":{"Multitrack":[0],"music":[1,7],"transcription":[2],"aims":[3],"to":[4,31,77,104,122,140],"transcribe":[5],"a":[6,20,27,60,69,96,130,137,150],"audio":[8,83],"input":[9,84],"into":[10],"the":[11,52,79,91,112,158,162],"musical":[12],"notes":[13],"of":[14,43,62,82,114,126],"multiple":[15],"instruments":[16,128],"simultaneously.":[17],"It":[18],"is":[19],"very":[21],"challenging":[22],"task":[23],"that":[24,116,157],"typically":[25],"requires":[26],"more":[28],"complex":[29],"model":[30,78,105,110,141],"achieve":[32],"satisfactory":[33],"result.":[34],"In":[35,64,133],"addition,":[36],"prior":[37],"works":[38],"mostly":[39],"focus":[40],"on":[41,169],"transcriptions":[42,125],"regular":[44],"instruments,":[45],"however,":[46],"neglecting":[47],"vocals,":[48],"which":[49],"are":[50],"usually":[51],"most":[53],"important":[54],"signal":[55],"source":[56],"if":[57],"present":[58],"in":[59,129,149],"piece":[61],"music.":[63],"this":[65],"paper,":[66],"we":[67,135],"propose":[68],"novel":[70],"deep":[71],"neural":[72],"network":[73],"architecture,":[74],"Perceiver":[75,88,92,115,138],"TF,":[76],"time-frequency":[80],"representation":[81],"for":[85],"multitrack":[86],"transcription.":[87],"TF":[89,139],"augments":[90],"architecture":[93],"by":[94],"introducing":[95],"hierarchical":[97],"expansion":[98],"with":[99],"an":[100],"additional":[101],"Transformer":[102],"layer":[103],"temporal":[106],"coherence.":[107],"Accordingly,":[108],"our":[109],"inherits":[111],"benefits":[113],"posses":[117],"better":[118],"scalability,":[119],"allowing":[120],"it":[121],"well":[123,146],"handle":[124],"many":[127],"single":[131],"model.":[132],"experiments,":[134],"train":[136],"12":[142],"instrument":[143],"classes":[144],"as":[145,147],"vocal":[148],"multi-task":[151],"learning":[152],"manner.":[153],"Our":[154],"result":[155],"demonstrates":[156],"proposed":[159],"system":[160],"outperforms":[161],"state-of-the-art":[163],"counterparts":[164],"(e.g.,":[165],"MT3":[166],"and":[167],"SpecTNT)":[168],"various":[170],"public":[171],"datasets.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":12},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
