{"id":"https://openalex.org/W2899260162","doi":"https://doi.org/10.1109/icassp.2019.8683426","title":"Multitask Learning for Frame-level Instrument Recognition","display_name":"Multitask Learning for Frame-level Instrument Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2899260162","doi":"https://doi.org/10.1109/icassp.2019.8683426","mag":"2899260162"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5005504900","display_name":"Yun-Ning Hung","orcid":"https://orcid.org/0000-0002-7242-6903"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yun-Ning Hung","raw_affiliation_strings":["Academia Sinica, Research Center for IT Innovation, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Research Center for IT Innovation, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626873","display_name":"Yi\u2010An Chen","orcid":"https://orcid.org/0000-0002-6889-5213"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-An Chen","raw_affiliation_strings":["KKBOX Inc., Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KKBOX Inc., Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica, Research Center for IT Innovation, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academia Sinica, Research Center for IT Innovation, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1611,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.96611033,"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":"381","last_page":"385"},"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":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8157058954238892},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.7021269202232361},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6501046419143677},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6007475256919861},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5230639576911926},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.4826934337615967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4690307378768921},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.43568649888038635},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43254974484443665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4238203763961792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3616793155670166},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08105036616325378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8157058954238892},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.7021269202232361},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6501046419143677},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6007475256919861},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5230639576911926},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.4826934337615967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690307378768921},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.43568649888038635},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43254974484443665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4238203763961792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3616793155670166},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08105036616325378},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683426","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683426","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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":37,"referenced_works":["https://openalex.org/W1590102137","https://openalex.org/W1901129140","https://openalex.org/W2065495703","https://openalex.org/W2095401277","https://openalex.org/W2098796164","https://openalex.org/W2107328928","https://openalex.org/W2127615536","https://openalex.org/W2164877274","https://openalex.org/W2191779130","https://openalex.org/W2261407818","https://openalex.org/W2296724634","https://openalex.org/W2407685581","https://openalex.org/W2475687244","https://openalex.org/W2559688696","https://openalex.org/W2593116425","https://openalex.org/W2773294482","https://openalex.org/W2885570506","https://openalex.org/W2903137797","https://openalex.org/W2903539539","https://openalex.org/W2962866891","https://openalex.org/W2963045359","https://openalex.org/W2963493667","https://openalex.org/W2964011431","https://openalex.org/W2964235767","https://openalex.org/W6635274319","https://openalex.org/W6639824700","https://openalex.org/W6692946518","https://openalex.org/W6697040288","https://openalex.org/W6714030504","https://openalex.org/W6721020019","https://openalex.org/W6730401039","https://openalex.org/W6734260513","https://openalex.org/W6746836464","https://openalex.org/W6752254909","https://openalex.org/W6753544557","https://openalex.org/W6756597712","https://openalex.org/W6756873980"],"related_works":["https://openalex.org/W3021272668","https://openalex.org/W2803309984","https://openalex.org/W2963872552","https://openalex.org/W2237537322","https://openalex.org/W2950678851","https://openalex.org/W2914746235","https://openalex.org/W4301248618","https://openalex.org/W2952195321","https://openalex.org/W4226202022","https://openalex.org/W2389546251"],"abstract_inverted_index":{"For":[0,170],"many":[1],"music":[2,55,110],"analysis":[3],"problems,":[4],"we":[5,43,63,172],"need":[6],"to":[7,33,71,92,177,182],"know":[8],"the":[9,34,74,86,94,98,105,112,117,123,133,136,158,161,175,179,184],"presence":[10],"of":[11,36,109,116,135,160],"instruments":[12,124],"for":[13,78,139,164],"each":[14,79,127],"time":[15],"frame":[16],"in":[17,45],"a":[18,24,48,65],"multi-instrument":[19],"musical":[20],"piece.":[21],"However,":[22],"such":[23],"frame-level":[25,57,140],"instrument":[26,60,77,141],"recognition":[27,142],"task":[28],"remains":[29],"difficult,":[30],"mainly":[31],"due":[32],"lack":[35],"labeled":[37],"datasets.":[38],"To":[39],"address":[40],"this":[41,46,82],"issue,":[42],"present":[44],"paper":[47],"large-scale":[49],"dataset":[50],"that":[51,125],"contains":[52],"synthetic":[53],"polyphonic":[54],"with":[56,146,167],"pitch":[58,75,87],"and":[59,76,96,151,181],"labels.":[61],"Moreover,":[62],"propose":[64],"simple":[66],"yet":[67],"novel":[68],"network":[69],"architecture":[70],"jointly":[72],"predict":[73,93],"frame.":[80],"With":[81],"multitask":[83],"learning":[84],"method,":[85],"information":[88],"can":[89],"be":[90],"leveraged":[91],"instruments,":[95],"also":[97,121,156],"other":[99],"way":[100],"around.":[101],"And,":[102],"by":[103,143],"using":[104],"so-called":[106],"pianoroll":[107],"representation":[108],"as":[111],"main":[113],"target":[114],"output":[115],"model,":[118],"our":[119],"model":[120,186],"predicts":[122],"play":[126],"individual":[128],"note":[129],"event.":[130],"We":[131,155],"validate":[132],"effectiveness":[134],"proposed":[137,162,185],"method":[138,163],"comparing":[144],"it":[145],"its":[147],"single-task":[148],"ablated":[149],"versions":[150],"three":[152],"state-of-the-art":[153],"methods.":[154],"demonstrate":[157],"result":[159],"multi-pitch":[165],"streaming":[166],"real-world":[168],"music.":[169],"reproducibility,":[171],"will":[173],"share":[174],"code":[176],"crawl":[178],"data":[180],"implement":[183],"at:":[187],"https://github.com/biboamy/":[188],"instrument-streaming.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
