{"id":"https://openalex.org/W2798069802","doi":"https://doi.org/10.1109/taslp.2018.2825108","title":"Online, Loudness-Invariant Vocal Detection in Mixed Music Signals","display_name":"Online, Loudness-Invariant Vocal Detection in Mixed Music Signals","publication_year":2018,"publication_date":"2018-04-09","ids":{"openalex":"https://openalex.org/W2798069802","doi":"https://doi.org/10.1109/taslp.2018.2825108","mag":"2798069802"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2825108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2825108","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5053582419","display_name":"Bernhard Lehner","orcid":"https://orcid.org/0000-0002-7754-7042"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Bernhard Lehner","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101525853","display_name":"Jan Schl\u00fcter","orcid":"https://orcid.org/0000-0003-3862-6888"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jan Schluter","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence, Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053582419"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":2.9726,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92209773,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"26","issue":"8","first_page":"1369","last_page":"1380"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/loudness","display_name":"Loudness","score":0.8420324325561523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7297056317329407},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7051653861999512},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.638057291507721},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6118196249008179},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5433370471000671},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5358133912086487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47381678223609924},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3778567314147949},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1405450403690338},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11215013265609741}],"concepts":[{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.8420324325561523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297056317329407},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7051653861999512},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.638057291507721},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6118196249008179},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5433370471000671},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5358133912086487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47381678223609924},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3778567314147949},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1405450403690338},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11215013265609741},{"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/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/taslp.2018.2825108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2825108","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2337039464","display_name":null,"funder_award_id":"NXT17-004","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"},{"id":"https://openalex.org/G2379990720","display_name":null,"funder_award_id":"Z159","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G2572961549","display_name":null,"funder_award_id":"TRP307-N23","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G7075013067","display_name":null,"funder_award_id":"MA14-018","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1499705833","https://openalex.org/W1519655822","https://openalex.org/W1583001605","https://openalex.org/W1601795611","https://openalex.org/W1608523847","https://openalex.org/W1668941714","https://openalex.org/W1964208564","https://openalex.org/W2007664495","https://openalex.org/W2023800933","https://openalex.org/W2031248101","https://openalex.org/W2054985402","https://openalex.org/W2064675550","https://openalex.org/W2085662862","https://openalex.org/W2091425152","https://openalex.org/W2098796164","https://openalex.org/W2123169318","https://openalex.org/W2124867748","https://openalex.org/W2125838338","https://openalex.org/W2130770109","https://openalex.org/W2139686264","https://openalex.org/W2143612262","https://openalex.org/W2144346840","https://openalex.org/W2160584856","https://openalex.org/W2170942820","https://openalex.org/W2207196656","https://openalex.org/W2288351922","https://openalex.org/W2293137601","https://openalex.org/W2401859649","https://openalex.org/W2405580681","https://openalex.org/W2406220897","https://openalex.org/W2406222150","https://openalex.org/W2903126092","https://openalex.org/W2917831833","https://openalex.org/W3019584399","https://openalex.org/W6630060122","https://openalex.org/W6631117800","https://openalex.org/W6680627905","https://openalex.org/W6696493858","https://openalex.org/W6697162658","https://openalex.org/W6713061376","https://openalex.org/W6713299141","https://openalex.org/W6713480825","https://openalex.org/W6756168015"],"related_works":["https://openalex.org/W1970025505","https://openalex.org/W2390529913","https://openalex.org/W2030358499","https://openalex.org/W1966585405","https://openalex.org/W2093863013","https://openalex.org/W2142368101","https://openalex.org/W2046078639","https://openalex.org/W2372249404","https://openalex.org/W2493561494","https://openalex.org/W2069086801"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"detection,":[2],"also":[3],"referred":[4],"to":[5,31,66,95,123,147,157,172,238],"as":[6,42,44,63,210],"vocal":[7],"detection":[8],"(VD),":[9],"aims":[10],"at":[11,21],"automatically":[12],"identifying":[13],"the":[14,32,38,45,69,140,150,153,173,193,213,221,239],"regions":[15],"in":[16,192],"a":[17,78,111,118,124,161,166,180,211],"music":[18],"recording":[19],"where":[20],"least":[22],"one":[23],"person":[24],"sings.":[25],"It":[26],"is":[27,83,92,106,201],"highly":[28],"challenging":[29,99],"due":[30,65,237],"timbral":[33],"and":[34,187,227],"expressive":[35],"richness":[36],"of":[37,49,60,68,103,121,152,169,215,223,242],"human":[39],"singing":[40],"voice,":[41],"well":[43],"practically":[46],"endless":[47],"variety":[48],"interfering":[50],"instrumental":[51],"accompaniment.":[52],"Additionally,":[53],"certain":[54],"instruments":[55],"have":[56],"an":[57],"inherent":[58],"risk":[59],"being":[61],"misclassified":[62],"vocals":[64],"similarities":[67],"sound":[70],"production":[71],"system.":[72],"In":[73,155],"this":[74,104,200,209,235],"paper,":[75],"we":[76,109,137,164,177],"present":[77,110],"machine":[79],"learning":[80],"approach":[81],"that":[82,116,132,183,229],"based":[84],"on":[85,179],"our":[86,230],"previous":[87],"work":[88],"for":[89,114,159,199],"VD,":[90],"which":[91],"specifically":[93],"designed":[94],"deal":[96],"with":[97,144,234],"those":[98],"conditions.":[100],"The":[101,197],"contribution":[102],"paper":[105],"threefold:":[107],"First,":[108],"new":[112],"method":[113,142,231],"VD":[115],"passes":[117],"compact":[119],"set":[120,241],"features":[122,226,243],"long":[125],"short-term":[126],"memory":[127],"recurrent":[128],"neural":[129],"network":[130],"classifier":[131],"obtains":[133],"state-of-the-art":[134],"results.":[135],"Second,":[136],"thoroughly":[138],"evaluate":[139],"proposed":[141],"along":[143],"related":[145],"approaches":[146],"really":[148],"probe":[149],"weaknesses":[151],"methods.":[154],"order":[156],"allow":[158],"such":[160],"thorough":[162],"evaluation,":[163],"make":[165],"curated":[167],"collection":[168],"datasets":[170],"available":[171],"research":[174],"community.":[175],"Finally,":[176],"focus":[178],"specific":[181,240],"problem":[182,236],"was":[184],"not":[185,189,207],"obvious":[186],"had":[188,206],"been":[190],"discussed":[191],"literature":[194],"so":[195],"far.":[196],"reason":[198],"precisely":[202],"because":[203],"limited":[204],"evaluations":[205],"revealed":[208],"problem:":[212],"lack":[214],"loudness":[216],"invariance.":[217],"We":[218],"will":[219],"discuss":[220],"implications":[222],"utilizing":[224],"loudness-related":[225],"show":[228],"successfully":[232],"deals":[233],"it":[244],"uses.":[245]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}