{"id":"https://openalex.org/W2122830402","doi":"https://doi.org/10.1109/aspaa.2009.5346497","title":"A novel framework for recognizing phonemes of singing voice in polyphonic music","display_name":"A novel framework for recognizing phonemes of singing voice in polyphonic music","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2122830402","doi":"https://doi.org/10.1109/aspaa.2009.5346497","mag":"2122830402"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2009.5346497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2009.5346497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","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/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":true,"raw_author_name":"Hiromasa Fujihara","raw_affiliation_strings":["Kyoto University, Kyoto, Japan","National Institute for Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan"],"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, Ibaraki, 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, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute for Advanced Industrial Science and Technology, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"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"],"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":["https://openalex.org/A5110207817"],"corresponding_institution_ids":["https://openalex.org/I22299242","https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":1.4284,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81465517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"17","last_page":"20"},"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":0.9995999932289124,"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":0.9957000017166138,"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/singing","display_name":"Singing","score":0.9414942264556885},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.9091711640357971},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8107080459594727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6991844177246094},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.6739605665206909},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.500089168548584},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4164234697818756},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4117547273635864},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32867711782455444},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08142438530921936}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9414942264556885},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9091711640357971},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8107080459594727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991844177246094},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.6739605665206909},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.500089168548584},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4164234697818756},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4117547273635864},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32867711782455444},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08142438530921936},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aspaa.2009.5346497","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2009.5346497","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.2763","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.2763","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/WASPAA2009fujihara.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W178884067","https://openalex.org/W1519655822","https://openalex.org/W1979188593","https://openalex.org/W2060998236","https://openalex.org/W2088867696","https://openalex.org/W2101119896","https://openalex.org/W2109703216","https://openalex.org/W2142714559","https://openalex.org/W2150884987","https://openalex.org/W2164282073","https://openalex.org/W2164336224","https://openalex.org/W2398871418","https://openalex.org/W6607294247","https://openalex.org/W6631117800","https://openalex.org/W6673181052","https://openalex.org/W6676245295","https://openalex.org/W6681343233","https://openalex.org/W6712736788"],"related_works":["https://openalex.org/W254868496","https://openalex.org/W2073905179","https://openalex.org/W2807674213","https://openalex.org/W2928432034","https://openalex.org/W1507952878","https://openalex.org/W4200277070","https://openalex.org/W1989331194","https://openalex.org/W4300740495","https://openalex.org/W2343253662","https://openalex.org/W1969398023"],"abstract_inverted_index":{"A":[0],"novel":[1],"method":[2,32,52,69,123],"is":[3,33,53],"described":[4],"that":[5,121],"can":[6,88],"be":[7,56],"used":[8],"to":[9,35,55],"recognize":[10,37],"the":[11,25,84,125],"phoneme":[12,27,110],"of":[13,40,74,109],"a":[14,41,57,62,72,75,91,133],"singing":[15,42,63,76,85],"voice":[16,43,64,77],"(vocal)":[17],"in":[18,28,65,136],"polyphonic":[19,66],"music.":[20,67],"Though":[21],"we":[22],"focus":[23],"on":[24],"voiced":[26],"this":[29,31,51],"paper,":[30],"design":[34],"concurrently":[36],"other":[38,79],"elements":[39],"such":[44],"as":[45],"fundamental":[46,104],"frequency":[47],"and":[48,78,131],"singer.":[49],"Thus,":[50],"considered":[54],"new":[58],"framework":[59],"for":[60],"recognizing":[61],"Our":[68],"stochastically":[70],"models":[71],"mixture":[73],"instrumental":[80],"sounds":[81],"without":[82],"segregating":[83],"voice.":[86],"It":[87],"also":[89],"estimate":[90],"reliable":[92],"spectral":[93],"envelope":[94],"by":[95,117,128],"estimating":[96],"it":[97],"from":[98],"many":[99],"harmonic":[100],"structures":[101],"with":[102,113],"various":[103],"frequencies":[105],"(F0s).":[106],"The":[107],"results":[108],"recognition":[111,126],"experiments":[112],"10":[114],"popular-music":[115],"songs":[116],"6":[118],"singers":[119],"showed":[120],"our":[122],"improves":[124],"accuracy":[127],"8.7":[129],"points":[130],"achieves":[132],"20.0%":[134],"decrease":[135],"error":[137],"rate.":[138]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
