{"id":"https://openalex.org/W1580780811","doi":"https://doi.org/10.1109/icassp.2015.7177945","title":"Extracting singing voice from music recordings by cascading audio decomposition techniques","display_name":"Extracting singing voice from music recordings by cascading audio decomposition techniques","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1580780811","doi":"https://doi.org/10.1109/icassp.2015.7177945","mag":"1580780811"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7177945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5057320374","display_name":"Jonathan Driedger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jonathan Driedger","raw_affiliation_strings":["International Audio Laboratories Erlangen","International Audio Laboratories Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard Muller","raw_affiliation_strings":["International Audio Laboratories Erlangen","International Audio Laboratories Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6097,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90108689,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"58","issue":null,"first_page":"126","last_page":"130"},"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":0.9984999895095825,"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/singing","display_name":"Singing","score":0.9387919902801514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7573619484901428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6548645496368408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6198275089263916},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5337864756584167},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.49031785130500793},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18438485264778137}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9387919902801514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573619484901428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6548645496368408},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6198275089263916},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5337864756584167},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.49031785130500793},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18438485264778137},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7177945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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":27,"referenced_works":["https://openalex.org/W29021047","https://openalex.org/W87112183","https://openalex.org/W282757658","https://openalex.org/W1504438288","https://openalex.org/W1508756421","https://openalex.org/W1604012244","https://openalex.org/W1665484889","https://openalex.org/W1976069042","https://openalex.org/W2020335482","https://openalex.org/W2022668263","https://openalex.org/W2036339641","https://openalex.org/W2062710265","https://openalex.org/W2105921478","https://openalex.org/W2116244429","https://openalex.org/W2124539664","https://openalex.org/W2145962650","https://openalex.org/W2151785180","https://openalex.org/W2153309059","https://openalex.org/W2164098335","https://openalex.org/W2403272360","https://openalex.org/W2407513162","https://openalex.org/W2889679658","https://openalex.org/W6601165733","https://openalex.org/W6603655804","https://openalex.org/W6636121673","https://openalex.org/W6657159850","https://openalex.org/W6713555227"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"The":[0,30],"problem":[1],"of":[2,25,59,74,101,123,135,147],"extracting":[3],"singing":[4,46,60,136,158,179],"voice":[5,47,159,180],"from":[6,163],"music":[7,39,118],"recordings":[8],"has":[9],"received":[10],"increasing":[11],"research":[12],"interest":[13],"in":[14,111],"recent":[15],"years.":[16],"Many":[17],"proposed":[18],"decomposition":[19,109,127],"techniques":[20,110],"are":[21,78],"based":[22],"on":[23],"one":[24,42,49],"the":[26,45,51,64,68,85,99,117,148,157,161,164],"following":[27,63],"two":[28],"strategies.":[29,103],"first":[31,105],"approach":[32,66,96],"is":[33,128],"to":[34,83,115,131,141,154],"directly":[35,155],"decompose":[36],"a":[37,71,94,112,121],"given":[38],"recording":[40,69,119],"into":[41,70,120],"component":[43],"for":[44,50],"and":[48,80,160,168,183],"accompaniment":[52,162],"by":[53],"exploiting":[54],"knowledge":[55],"about":[56],"specific":[57],"characteristics":[58,134],"voice.":[61],"Procedures":[62],"second":[65],"disassemble":[67,116],"large":[72],"set":[73,122],"fine-grained":[75],"components,":[76],"which":[77],"classified":[79],"reassembled":[81],"afterwards":[82],"yield":[84],"desired":[86],"source":[87],"estimates.":[88],"In":[89],"this":[90,173],"paper,":[91],"we":[92],"propose":[93],"novel":[95],"that":[97,172],"combines":[98],"strengths":[100],"both":[102],"We":[104],"apply":[106],"different":[107],"audio":[108],"cascaded":[113],"fashion":[114],"mid-level":[124],"components.":[125,149,165],"This":[126],"fine":[129],"enough":[130,140],"model":[132],"various":[133],"voice,":[137],"but":[138],"coarse":[139],"keep":[142],"an":[143],"explicit":[144],"semantic":[145],"meaning":[146],"These":[150],"properties":[151],"allow":[152],"us":[153],"reassemble":[156],"Our":[166],"objective":[167],"subjective":[169],"evaluations":[170],"show":[171],"strategy":[174],"can":[175],"compete":[176],"with":[177],"state-of-the-art":[178],"separation":[181],"algorithms":[182],"yields":[184],"perceptually":[185],"appealing":[186],"results.":[187]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}