{"id":"https://openalex.org/W1965014312","doi":"https://doi.org/10.1109/icassp.2014.6854176","title":"Transcribing vocal expression from polyphonic music","display_name":"Transcribing vocal expression from polyphonic music","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1965014312","doi":"https://doi.org/10.1109/icassp.2014.6854176","mag":"1965014312"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5087321595","display_name":"Yukara Ikemiya","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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukara Ikemiya","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan","[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"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":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan","[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]","institution_ids":["https://openalex.org/I22299242"]}]},{"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":["Graduate School of Informatics, Kyoto University, Japan","[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"3127","last_page":"3131"},"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":0.9997000098228455,"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":0.9980999827384949,"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/vibrato","display_name":"Vibrato","score":0.9314970374107361},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9255268573760986},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8481833934783936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.747324526309967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624190628528595},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.5609712600708008},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5300050973892212},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4853743314743042},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4815412163734436},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.41104716062545776},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.31473034620285034},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.10518226027488708},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.07634109258651733}],"concepts":[{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.9314970374107361},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9255268573760986},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8481833934783936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.747324526309967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624190628528595},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5609712600708008},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5300050973892212},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4853743314743042},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4815412163734436},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.41104716062545776},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.31473034620285034},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.10518226027488708},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.07634109258651733},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6854176","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854176","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.467.3422","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.467.3422","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/members/ikemiya/paper/icassp-2014-ikemiya.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.494.9761","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.494.9761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/members/okuno/Public/ICASSP2014-Ikemiya.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5300062852","display_name":null,"funder_award_id":"24220006","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":36,"referenced_works":["https://openalex.org/W57034108","https://openalex.org/W109946471","https://openalex.org/W111300696","https://openalex.org/W178932670","https://openalex.org/W202653786","https://openalex.org/W368306927","https://openalex.org/W1519655822","https://openalex.org/W1582043709","https://openalex.org/W1592438470","https://openalex.org/W1965419851","https://openalex.org/W2023800933","https://openalex.org/W2030143463","https://openalex.org/W2045914913","https://openalex.org/W2073992179","https://openalex.org/W2076608692","https://openalex.org/W2098101267","https://openalex.org/W2100989275","https://openalex.org/W2101119896","https://openalex.org/W2108494558","https://openalex.org/W2111037747","https://openalex.org/W2124097505","https://openalex.org/W2166472876","https://openalex.org/W2396908887","https://openalex.org/W2403321691","https://openalex.org/W2404763528","https://openalex.org/W2408435475","https://openalex.org/W2885029858","https://openalex.org/W6602348752","https://openalex.org/W6612574609","https://openalex.org/W6631117800","https://openalex.org/W6635375625","https://openalex.org/W6678318511","https://openalex.org/W6712467414","https://openalex.org/W6713346638","https://openalex.org/W6713876852","https://openalex.org/W6753762981"],"related_works":["https://openalex.org/W4394924759","https://openalex.org/W2886940211","https://openalex.org/W1850879794","https://openalex.org/W4394925019","https://openalex.org/W1583791393","https://openalex.org/W2057725539","https://openalex.org/W2405700924","https://openalex.org/W982608558","https://openalex.org/W4225086757","https://openalex.org/W2012356996"],"abstract_inverted_index":{"A":[0],"method":[1,109],"for":[2,36,43],"transcribing":[3],"vocal":[4],"expressions":[5,19,112],"such":[6],"as":[7,21],"vibrato,":[8],"glissando,":[9],"and":[10,38,42,98],"kobushi":[11],"separately":[12],"from":[13,77,117],"polyphonic":[14],"music":[15,41],"is":[16,69,96],"described.":[17],"The":[18,61],"appear":[20],"fluctuation":[22],"in":[23,100,113],"the":[24,29,56,59,66,72,83,88,114],"fundamental":[25,62,89],"frequency":[26,63,90],"contour":[27,64],"of":[28,40,58,65],"singing":[30,45,50,67,115],"voice.":[31],"They":[32],"can":[33,110],"be":[34],"used":[35],"search":[37],"retrieval":[39],"expressive":[44],"voice":[46,68,116],"synthesis":[47],"based":[48],"on":[49],"style":[51],"since":[52],"they":[53],"strongly":[54],"reflect":[55],"individuality":[57],"singer.":[60],"estimated":[70],"using":[71],"Viterbi":[73],"algorithm":[74],"with":[75,87,102],"limitation":[76],"a":[78],"corresponding":[79],"note":[80],"sequence.":[81],"Next,":[82],"notes":[84],"are":[85],"aligned":[86],"sequence":[91],"temporally.":[92],"Finally,":[93],"each":[94],"expression":[95],"identified":[97],"parameterized":[99],"accordance":[101],"designed":[103],"rules.":[104],"Experiments":[105],"demonstrated":[106],"that":[107],"this":[108],"transcribe":[111],"commercial":[118],"recordings.":[119]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
