{"id":"https://openalex.org/W3009039098","doi":"https://doi.org/10.1145/3377325.3377539","title":"Interactive deep singing-voice separation based on human-in-the-loop adaptation","display_name":"Interactive deep singing-voice separation based on human-in-the-loop adaptation","publication_year":2020,"publication_date":"2020-03-04","ids":{"openalex":"https://openalex.org/W3009039098","doi":"https://doi.org/10.1145/3377325.3377539","mag":"3009039098"},"language":"en","primary_location":{"id":"doi:10.1145/3377325.3377539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377325.3377539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on Intelligent User Interfaces","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/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu Nakano","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049682921","display_name":"Yuki Koyama","orcid":"https://orcid.org/0000-0002-3978-1444"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Koyama","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017826395","display_name":"Masahiro Hamasaki","orcid":"https://orcid.org/0000-0003-3085-7446"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahiro Hamasaki","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9988999962806702,"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/adaptation","display_name":"Adaptation (eye)","score":0.691834568977356},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6762080192565918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377830505371094},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.5804598331451416},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5788169503211975},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5354322195053101},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49814701080322266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3093416690826416},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19613409042358398},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08815166354179382},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08690065145492554},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08062440156936646},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07246837019920349},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06573697924613953}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.691834568977356},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6762080192565918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377830505371094},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.5804598331451416},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5788169503211975},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5354322195053101},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49814701080322266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3093416690826416},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19613409042358398},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08815166354179382},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08690065145492554},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08062440156936646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07246837019920349},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06573697924613953},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377325.3377539","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377325.3377539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W68855703","https://openalex.org/W192032276","https://openalex.org/W1501005121","https://openalex.org/W1578924114","https://openalex.org/W2003020982","https://openalex.org/W2004959592","https://openalex.org/W2090625014","https://openalex.org/W2116244429","https://openalex.org/W2130770109","https://openalex.org/W2141061845","https://openalex.org/W2149368536","https://openalex.org/W2152591660","https://openalex.org/W2168509488","https://openalex.org/W2291378481","https://openalex.org/W2296724634","https://openalex.org/W2300469113","https://openalex.org/W2405258286","https://openalex.org/W2407685581","https://openalex.org/W2516392987","https://openalex.org/W2552071709","https://openalex.org/W2763160469","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2809183397","https://openalex.org/W2902808043","https://openalex.org/W2906098386","https://openalex.org/W2963249619","https://openalex.org/W2963452667","https://openalex.org/W2963750251","https://openalex.org/W2986673441","https://openalex.org/W2997938083"],"related_works":["https://openalex.org/W189527659","https://openalex.org/W2791504333","https://openalex.org/W3207249698","https://openalex.org/W1571518467","https://openalex.org/W87991986","https://openalex.org/W1528909574","https://openalex.org/W2122830402","https://openalex.org/W1543657218","https://openalex.org/W4223953616","https://openalex.org/W2135121413"],"abstract_inverted_index":{"This":[0,65],"paper":[1],"presents":[2],"a":[3,42,46,173,191,205],"deep-learning-based":[4],"interactive":[5],"system":[6,202],"separating":[7],"the":[8,37,51,62,85,94,98,102,106,111,120,124,136,147,152,155,159,178,183],"singing":[9,24,112],"voice":[10,25],"from":[11,97],"input":[12,99],"polyphonic":[13,100],"music":[14],"signals.":[15],"Although":[16,114],"deep":[17,52],"neural":[18,53],"networks":[19,71,145],"have":[20],"been":[21],"successful":[22],"for":[23,35,83,104,119],"separation,":[26],"no":[27],"approach":[28,171],"using":[29],"them":[30],"allows":[31,45],"any":[32],"user":[33,47,121,193],"interaction":[34],"improving":[36],"separation":[38,166,208],"quality.":[39,167],"We":[40,168,188],"present":[41],"framework":[43],"that":[44,88,177],"to":[48,58,61,92,122,150,203],"interactively":[49],"fine-tune":[50],"model":[54,160],"at":[55],"run":[56],"time":[57],"adapt":[59],"it":[60,115],"target":[63],"song.":[64],"is":[66,116],"enabled":[67],"by":[68],"designing":[69],"unified":[70,144],"consisting":[72],"of":[73,110,135,154,185],"two":[74],"U-Net":[75],"architectures":[76],"based":[77],"on":[78],"frequency":[79,108],"spectrogram":[80,86,96],"representations:":[81],"one":[82],"estimating":[84,105],"mask":[87],"can":[89,129,181],"be":[90],"used":[91,200],"extract":[93],"singing-voice":[95,186,207],"spectrogram;":[101],"other":[103],"fundamental":[107],"(F0)":[109],"voice.":[113],"not":[117],"easy":[118],"edit":[123],"mask,":[125],"he":[126],"or":[127],"she":[128],"iteratively":[130],"correct":[131],"errors":[132],"in":[133,164,172],"part":[134],"visualized":[137],"F0":[138,149,156,179],"trajectory":[139,157],"through":[140,158],"simple":[141],"interaction.":[142],"Our":[143],"leverage":[146],"user-corrected":[148],"improve":[151,182],"rest":[153],"adaptation,":[161],"which":[162],"results":[163],"better":[165],"validated":[169],"this":[170],"simulation":[174],"experiment":[175],"showing":[176],"correction":[180],"quality":[184],"separation.":[187],"also":[189],"conducted":[190],"pilot":[192],"study":[194],"with":[195],"an":[196],"expert":[197],"musician,":[198],"who":[199],"our":[201],"produce":[204],"high-quality":[206],"result.":[209]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}