{"id":"https://openalex.org/W2152591660","doi":"https://doi.org/10.1109/tasl.2010.2041386","title":"A Modeling of Singing Voice Robust to Accompaniment Sounds and Its Application to Singer Identification and Vocal-Timbre-Similarity-Based Music Information Retrieval","display_name":"A Modeling of Singing Voice Robust to Accompaniment Sounds and Its Application to Singer Identification and Vocal-Timbre-Similarity-Based Music Information Retrieval","publication_year":2010,"publication_date":"2010-02-16","ids":{"openalex":"https://openalex.org/W2152591660","doi":"https://doi.org/10.1109/tasl.2010.2041386","mag":"2152591660"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2041386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041386","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2433/131955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110207817","display_name":"Hiromasa Fujihara","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"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":"Hiromasa Fujihara","raw_affiliation_strings":["Kyoto University, Kyoto, Japan","National Institute for Advanced Industrial Science and Technology, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","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 for Advanced Industrial Science and Technology, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108346747","display_name":"Tetsuro Kitahara","orcid":null},"institutions":[{"id":"https://openalex.org/I206011266","display_name":"Kwansei Gakuin University","ror":"https://ror.org/02qf2tx24","country_code":"JP","type":"education","lineage":["https://openalex.org/I206011266"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuro Kitahara","raw_affiliation_strings":["Kwansei Gakuin University, Hyogo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwansei Gakuin University, Hyogo, Japan","institution_ids":["https://openalex.org/I206011266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.0016,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.98143957,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"638","last_page":"648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9952999949455261,"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/timbre","display_name":"Timbre","score":0.9237385988235474},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9087420701980591},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7631658315658569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6284118890762329},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6077038645744324},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5462401509284973},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.5401623845100403},{"id":"https://openalex.org/keywords/pitch","display_name":"Pitch (Music)","score":0.4957062005996704},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4668481945991516},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.45921632647514343},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4524567723274231},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4303112328052521},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.4199731647968292},{"id":"https://openalex.org/keywords/musical-tone","display_name":"Musical tone","score":0.41105133295059204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3632274866104126},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.339799165725708},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26835718750953674},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1461605727672577},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09074714779853821}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9237385988235474},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9087420701980591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7631658315658569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6284118890762329},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6077038645744324},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5462401509284973},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.5401623845100403},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.4957062005996704},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4668481945991516},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.45921632647514343},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4524567723274231},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4303112328052521},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.4199731647968292},{"id":"https://openalex.org/C86011254","wikidata":"https://www.wikidata.org/wiki/Q2717062","display_name":"Musical tone","level":4,"score":0.41105133295059204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3632274866104126},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.339799165725708},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26835718750953674},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1461605727672577},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09074714779853821},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tasl.2010.2041386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041386","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000095928","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/131955","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.7635","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.7635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.aist.go.jp/h.fujihara/pdf/ieee2010_fujihara.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.2960","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.2960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.aist.go.jp/m.goto/PAPER/IEEETASLP201003fujihara.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01221:0000095928","is_oa":true,"landing_page_url":"http://hdl.handle.net/2433/131955","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G4639212479","display_name":"Development of Robot Audition based on Computational Auditory Scene Analysis","funder_award_id":"19100003","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W42784339","https://openalex.org/W48943499","https://openalex.org/W131293899","https://openalex.org/W145820976","https://openalex.org/W153815065","https://openalex.org/W172720284","https://openalex.org/W190117771","https://openalex.org/W1519655822","https://openalex.org/W1570504315","https://openalex.org/W1590833177","https://openalex.org/W1832115024","https://openalex.org/W2023800933","https://openalex.org/W2046059186","https://openalex.org/W2050693797","https://openalex.org/W2081401329","https://openalex.org/W2100354557","https://openalex.org/W2107058149","https://openalex.org/W2107252339","https://openalex.org/W2138084857","https://openalex.org/W2153146266","https://openalex.org/W2154591323","https://openalex.org/W2156063339","https://openalex.org/W2165320163","https://openalex.org/W2394955069","https://openalex.org/W3134246028","https://openalex.org/W6601727801","https://openalex.org/W6602025118","https://openalex.org/W6605236737","https://openalex.org/W6605978473","https://openalex.org/W6606268758","https://openalex.org/W6607028168","https://openalex.org/W6607765636","https://openalex.org/W6631117800","https://openalex.org/W6634309418","https://openalex.org/W6635558701","https://openalex.org/W6675412913","https://openalex.org/W6682825961","https://openalex.org/W6712099778"],"related_works":["https://openalex.org/W2171508519","https://openalex.org/W55541205","https://openalex.org/W4253259713","https://openalex.org/W2946308721","https://openalex.org/W1982918643","https://openalex.org/W1559970579","https://openalex.org/W4253022192","https://openalex.org/W654690113","https://openalex.org/W2088426425","https://openalex.org/W2111280290"],"abstract_inverted_index":{"This":[0,186],"paper":[1],"describes":[2],"a":[3,10,53,95,99,126],"method":[4,135],"of":[5,9,20,52,98,112,140,142,149,170,182,189,199],"modeling":[6,49],"the":[7,50,57,109,113,122,138,143,147,166,183,190,197],"characteristics":[8,51],"singing":[11,25,54,100,191],"voice":[12,55,101,192],"from":[13,116],"polyphonic":[14],"musical":[15,22,32,171],"audio":[16],"signals":[17],"including":[18],"sounds":[19],"various":[21],"instruments.":[23],"Because":[24],"voices":[26],"play":[27],"an":[28,200,208],"important":[29],"role":[30],"in":[31,48],"pieces":[33],"with":[34],"vocals,":[35],"such":[36],"representation":[37,188],"is":[38,56,176,193],"useful":[39],"for":[40,159],"music":[41],"information":[42],"retrieval":[43],"systems.":[44],"The":[45,84,133],"main":[46],"problem":[47],"negative":[58],"influences":[59],"caused":[60],"by":[61,124,130,152,178],"accompaniment":[62,104,150],"sounds.":[63,105],"To":[64],"solve":[65],"this":[66],"problem,":[67],"we":[68],"developed":[69],"two":[70,154],"methods,":[71],"<i":[72],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[73,82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">accompaniment":[74],"sound":[75,117],"reduction":[76],"and":[77,119,161,205],"reliable":[78,167,184],"frame":[79,141],"selection</i>":[80],"<b":[81],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">.</b>":[83],"former":[85],"makes":[86],"it":[87],"possible":[88],"to":[89,164,195,206],"calculate":[90],"feature":[91],"vectors":[92],"that":[93],"represent":[94],"spectral":[96],"envelope":[97],"after":[102],"reducing":[103],"It":[106],"first":[107],"extracts":[108],"harmonic":[110],"components":[111],"predominant":[114],"melody":[115,123,145],"mixtures":[118],"then":[120,136],"resynthesizes":[121],"using":[125,153],"sinusoidal":[127],"model":[128],"driven":[129],"these":[131],"components.":[132],"latter":[134],"estimates":[137],"reliability":[139],"obtained":[144],"(i.e.,":[146],"influence":[148],"sound)":[151],"Gaussian":[155],"mixture":[156],"models":[157],"(GMMs)":[158],"vocal":[160,168,213],"nonvocal":[162],"frames":[163],"select":[165],"portions":[169],"pieces.":[172],"Finally,":[173],"each":[174],"song":[175],"represented":[177],"its":[179],"GMM":[180],"consisting":[181],"frames.":[185],"new":[187],"demonstrated":[194],"improve":[196],"performance":[198],"automatic":[201],"singer":[202],"identification":[203],"system":[204,210],"achieve":[207],"MIR":[209],"based":[211],"on":[212],"timbre":[214],"similarity.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
