{"id":"https://openalex.org/W2101119896","doi":"https://doi.org/10.1109/icassp.2006.1661260","title":"F0 Estimation Method for Singing Voice in Polyphonic Audio Signal Based on Statistical Vocal Model and Viterbi Search","display_name":"F0 Estimation Method for Singing Voice in Polyphonic Audio Signal Based on Statistical Vocal Model and Viterbi Search","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2101119896","doi":"https://doi.org/10.1109/icassp.2006.1661260","mag":"2101119896"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1661260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"H. Fujihara","raw_affiliation_strings":["Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Dept. of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan. fujihara, kitahara@kuis.kyoto-u.ac.jp"],"affiliations":[{"raw_affiliation_string":"Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Dept. of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Sakyo-ku, Kyoto 606-8501, Japan. fujihara, kitahara@kuis.kyoto-u.ac.jp","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076173920","display_name":"T Kitahara","orcid":"https://orcid.org/0000-0002-5347-7924"},"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":"T. Kitahara","raw_affiliation_strings":["Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Dept. of Intelligence Sci. & Technol., Kyoto Univ.#TAB#"],"affiliations":[{"raw_affiliation_string":"Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Dept. of Intelligence Sci. & Technol., Kyoto Univ.#TAB#","institution_ids":["https://openalex.org/I22299242"]}]},{"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":"M. Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","National Institute of Advanced Industrial Science and Techno"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Techno","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"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/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Komatani","raw_affiliation_strings":["Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055922202","display_name":"Tetsuya Ogata","orcid":"https://orcid.org/0000-0001-7015-0379"},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"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":"T. Ogata","raw_affiliation_strings":["Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Dept. of Intelligence Science and Technology, Kyoto University, Sakyo-ku, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013431417","display_name":"H.G. Okun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129581","display_name":"Kyoto University of Education","ror":"https://ror.org/03zhhr656","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210129581"]},{"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":"H.G. Okun","raw_affiliation_strings":["Kyoto univ"],"affiliations":[{"raw_affiliation_string":"Kyoto univ","institution_ids":["https://openalex.org/I22299242","https://openalex.org/I4210129581"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5110207817"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":null,"apc_paid":null,"fwci":4.1915,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.94371223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9970999956130981,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.8844717741012573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8269025683403015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7703922390937805},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7244268655776978},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6018149852752686},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5599076747894287},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5065127611160278},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3565160036087036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3356408476829529},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.28871068358421326},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21898549795150757}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8844717741012573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8269025683403015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703922390937805},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7244268655776978},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6018149852752686},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5599076747894287},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5065127611160278},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3565160036087036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3356408476829529},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.28871068358421326},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21898549795150757},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2006.1661260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.74.1438","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.74.1438","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/~okuno/paper/ICASSP2006-Fujihara.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":17,"referenced_works":["https://openalex.org/W99956014","https://openalex.org/W178884067","https://openalex.org/W188353524","https://openalex.org/W200190320","https://openalex.org/W1519655822","https://openalex.org/W2023800933","https://openalex.org/W2107058149","https://openalex.org/W2118938505","https://openalex.org/W2124867748","https://openalex.org/W2144031951","https://openalex.org/W6604047900","https://openalex.org/W6607294247","https://openalex.org/W6607540946","https://openalex.org/W6608199584","https://openalex.org/W6631117800","https://openalex.org/W6675746282","https://openalex.org/W6681260918"],"related_works":["https://openalex.org/W178932670","https://openalex.org/W182406043","https://openalex.org/W2098448993","https://openalex.org/W2342965987","https://openalex.org/W2189603775","https://openalex.org/W86529187","https://openalex.org/W2159113005","https://openalex.org/W2516392987","https://openalex.org/W2115124682","https://openalex.org/W2101119896"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,19,77],"method":[4,116],"for":[5,35],"estimating":[6],"F0s":[7,28],"of":[8,27,29,49,53,64,128],"vocal":[9,31,47,62,88,92],"from":[10,120],"polyphonic":[11],"audio":[12],"signals.":[13],"Because":[14],"melody":[15],"is":[16,33,125],"sung":[17],"by":[18,75,90],"singer":[20],"in":[21],"many":[22,36],"musical":[23],"pieces,":[24],"the":[25,30,46,50,61,65,72,87],"estimation":[26,42,118],"part":[32],"useful":[34],"applications.":[37],"Based":[38],"on":[39,108],"existing":[40],"multiple-F0":[41],"method,":[43],"we":[44,68,85,100],"evaluate":[45,86],"probabilities":[48,63,106],"harmonic":[51,66,73],"structure":[52,74],"each":[54],"F0":[55,102],"candidate.":[56],"In":[57],"order":[58],"to":[59,122],"calculate":[60],"structure,":[67],"extract":[69,81],"and":[70,80,93],"resynthesize":[71],"using":[76,91,104],"sinusoidal":[78],"model":[79],"feature":[82],"vectors.":[83],"Then,":[84],"probability":[89],"non-vocal":[94],"Gaussian":[95],"mixture":[96],"models":[97],"(GMMs).":[98],"Finally,":[99],"track":[101],"trajectories":[103],"these":[105],"based":[107],"Viterbi":[109],"search.":[110],"Experimental":[111],"results":[112],"show":[113],"that":[114],"our":[115],"improves":[117],"accuracy":[119],"78.1%":[121],"84.3%,":[123],"which":[124],"28.3%":[126],"reduction":[127],"misestimation":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
