{"id":"https://openalex.org/W322498491","doi":"https://doi.org/10.21437/interspeech.2009-496","title":"Observation of empirical cumulative distribution of vowel spectral distances and its application to vowel based voice conversion","display_name":"Observation of empirical cumulative distribution of vowel spectral distances and its application to vowel based voice conversion","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W322498491","doi":"https://doi.org/10.21437/interspeech.2009-496","mag":"322498491"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5072749858","display_name":"Hideki Kawahara","orcid":"https://orcid.org/0000-0001-9360-5700"},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Kawahara","raw_affiliation_strings":["Wakayama University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wakayama University","institution_ids":["https://openalex.org/I75198481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075267422","display_name":"Masanori Morise","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":"Masanori Morise","raw_affiliation_strings":["Kwansei Gakuin University, Nishinomiya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kwansei Gakuin University, Nishinomiya, Japan","institution_ids":["https://openalex.org/I206011266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065967819","display_name":"T\u00f4ru Takahashi","orcid":"https://orcid.org/0000-0002-8476-9751"},"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":"Toru Takahashi","raw_affiliation_strings":["Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112229869","display_name":"Hideki Banno","orcid":null},"institutions":[{"id":"https://openalex.org/I96636082","display_name":"Meijo University","ror":"https://ror.org/04h42fc75","country_code":"JP","type":"education","lineage":["https://openalex.org/I96636082"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Banno","raw_affiliation_strings":["Meijo University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meijo University, Nagoya, Japan","institution_ids":["https://openalex.org/I96636082"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090747857","display_name":"Ryuichi Nisimura","orcid":null},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Nisimura","raw_affiliation_strings":["Wakayama University, Wakayama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wakayama University, Wakayama, Japan","institution_ids":["https://openalex.org/I75198481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078342732","display_name":"Toshio Irino","orcid":"https://orcid.org/0000-0002-7691-4189"},"institutions":[{"id":"https://openalex.org/I75198481","display_name":"Wakayama University","ror":"https://ror.org/05wr49d48","country_code":"JP","type":"education","lineage":["https://openalex.org/I75198481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshio Irino","raw_affiliation_strings":["Wakayama University, Wakayama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wakayama University, Wakayama, Japan","institution_ids":["https://openalex.org/I75198481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2437,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42076328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2647","last_page":"2650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},{"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.928752064704895},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.7751070261001587},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6929984092712402},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.547025740146637},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5405188798904419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5233099460601807},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41241320967674255},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.40137729048728943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3630847930908203},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12175372242927551}],"concepts":[{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.928752064704895},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.7751070261001587},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6929984092712402},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.547025740146637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5405188798904419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5233099460601807},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41241320967674255},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.40137729048728943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3630847930908203},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12175372242927551},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2009-496","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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":9,"referenced_works":["https://openalex.org/W104734300","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2062699140","https://openalex.org/W2082557891","https://openalex.org/W2115606020","https://openalex.org/W2131062138","https://openalex.org/W2140533244","https://openalex.org/W2166500461"],"related_works":["https://openalex.org/W1911592522","https://openalex.org/W2050311283","https://openalex.org/W2087669554","https://openalex.org/W3044757496","https://openalex.org/W2040757176","https://openalex.org/W3109318984","https://openalex.org/W2622171161","https://openalex.org/W2766167392","https://openalex.org/W1967583338","https://openalex.org/W2048127514"],"abstract_inverted_index":{"A":[0],"simple":[1],"and":[2,61,80,97,118],"fast":[3],"voice":[4,131,138],"conversion":[5,132],"method":[6,16,112,117,128],"based":[7],"only":[8],"on":[9,18],"vowel":[10,30,43,49,69,91,141],"information":[11],"is":[12,113,119],"proposed.":[13],"The":[14,110],"proposed":[15,111,127],"relies":[17],"empirical":[19,56],"distribution":[20,57],"of":[21,28,42,63,94,125],"perceptual":[22],"spectral":[23,35,70,144],"distances":[24],"between":[25,90],"representative":[26],"examples":[27],"each":[29],"segment":[31],"extracted":[32],"using":[33],"TANDEM-STRAIGHT":[34],"envelope":[36],"estimation":[37],"procedure":[38],"[1].":[39],"Mapping":[40],"functions":[41],"spectra":[44,93],"are":[45,133],"designed":[46],"to":[47],"preserve":[48],"space":[50],"structure":[51,65],"defined":[52],"by":[53],"the":[54,64,95,98,126],"observed":[55],"while":[58],"transforming":[59],"position":[60],"orientation":[62],"in":[66,76,86,107],"an":[67],"abstract":[68],"space.":[71],"By":[72],"introducing":[73],"physiological":[74],"constraints":[75],"vocal":[77,81,146],"tract":[78,82,147],"shapes":[79],"length":[83,148],"normalization,":[84],"difficulties":[85],"careful":[87],"frequency":[88],"alignment":[89],"template":[92],"source":[96],"target":[99],"speakers":[100],"can":[101],"be":[102],"alleviated":[103],"without":[104],"significant":[105],"degradations":[106],"converted":[108],"speech.":[109],"a":[114],"framebased":[115],"instantaneous":[116],"relevant":[120],"for":[121],"real-time":[122],"processing.":[123],"Applications":[124],"in-cross":[129],"language":[130],"also":[134],"discussed.":[135],"Index":[136],"Terms:":[137],"conversion,":[139],"STRAIGHT,":[140],"structure,":[142],"line":[143],"pair,":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
