{"id":"https://openalex.org/W2556797909","doi":"https://doi.org/10.1121/1.4969157","title":"Improvement of quality of voice conversion based on spectral differential filter using STRAIGHT-based Mel-cepstral coefficients","display_name":"Improvement of quality of voice conversion based on spectral differential filter using STRAIGHT-based Mel-cepstral coefficients","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2556797909","doi":"https://doi.org/10.1121/1.4969157","mag":"2556797909"},"language":"en","primary_location":{"id":"doi:10.1121/1.4969157","doi":"https://doi.org/10.1121/1.4969157","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.4969157","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Acoustical Society of America","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W2556797909"],"child_works_count":0,"type":"conference-abstract","is_traditional":false,"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/A5145228478","display_name":"\u5c0f\u6c60\u6cbb\u61b2","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Harunori Koike","raw_affiliation_strings":["Tohoku Univ., 6-6-05, Aoba, Aramaki, Aoba-ku, Sendai 980-8579, Japan, harunori.koike.q5@dc.tohoku.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku Univ., 6-6-05, Aoba, Aramaki, Aoba-ku, Sendai 980-8579, Japan, harunori.koike.q5@dc.tohoku.ac.jp","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019","observed_orcids":["https://orcid.org/0000-0001-5403-0019"]},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Tohoku Univ., 6-6-05, Aoba, Aramaki, Aoba-ku, Sendai 980-8579, Japan, harunori.koike.q5@dc.tohoku.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku Univ., 6-6-05, Aoba, Aramaki, Aoba-ku, Sendai 980-8579, Japan, harunori.koike.q5@dc.tohoku.ac.jp","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450","observed_orcids":["https://orcid.org/0000-0001-8114-8450"]},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698","https://openalex.org/I4400009020"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Inst. of Technol., Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Technol., Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877","observed_orcids":["https://orcid.org/0000-0002-8835-7877"]},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Tohoku Univ., Sendai, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku Univ., Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103144936","https://openalex.org/A5145228478"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"140","issue":"4_Supplement","first_page":"2963","last_page":"2963"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940999746322632,"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":0.9940999746322632,"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":0.005499999970197678,"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/T10863","display_name":"Voice and Speech Disorders","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice-conversion","display_name":"voice conversion","score":0.8529999852180481},{"id":"https://openalex.org/keywords/straight","display_name":"STRAIGHT","score":0.9679999947547913},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.8840000033378601},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"spectral envelope","score":0.7210000157356262},{"id":"https://openalex.org/keywords/dynamic-characteristics","display_name":"dynamic characteristics","score":0.6940000057220459},{"id":"https://openalex.org/keywords/waveform-conversion","display_name":"waveform conversion","score":0.6710000038146973},{"id":"https://openalex.org/keywords/speaker-individuality","display_name":"speaker individuality","score":0.4970000088214874},{"id":"https://openalex.org/keywords/speech-quality","display_name":"speech quality","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7060752511024475},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6753270626068115},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6572901010513306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6380106210708618},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5538305044174194},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5343859195709229},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4801289737224579},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.47508445382118225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4570664167404175},{"id":"https://openalex.org/C2777042112","wikidata":"https://www.wikidata.org/wiki/Q5281658","display_name":"Discontinuity (linguistics)","level":2,"score":0.4103161692619324},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3554110527038574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2345694601535797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22160738706588745},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2210991382598877},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07712322473526001},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06366324424743652},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/1.4969157","doi":"https://doi.org/10.1121/1.4969157","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.4969157","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Acoustical Society of America","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2849674871","display_name":"Self-Organized Learning of Speech Recognition and Synthesis Systems","funder_award_id":"26280055","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2357685141","https://openalex.org/W2979922415","https://openalex.org/W7145369803","https://openalex.org/W2120731853","https://openalex.org/W2586453598","https://openalex.org/W2120605154","https://openalex.org/W2162496900","https://openalex.org/W3108596716","https://openalex.org/W2182160202","https://openalex.org/W2032421775"],"abstract_inverted_index":{"In":[0],"our":[1],"previous":[2],"research,":[3],"we":[4,52,111,160,180],"proposed":[5,88,109],"a":[6,21,46,54],"technique":[7,26],"for":[8,32],"converting":[9],"the":[10,28,39,50,58,61,64,67,73,76,80,87,92,97,102,118,131,135,139,143,147,156,162,165,172,182,187,190,194],"speech":[11,14,69,122,196],"individuality":[12],"of":[13,15,41,60,63,75,86,121,130,138,146,155,164,167,189],"an":[16],"arbitrary":[17],"input":[18,77],"speaker":[19,78],"into":[20,79],"specified":[22],"speaker\u2019s":[23,82],"one.":[24,83],"This":[25],"used":[27],"neural":[29],"network":[30],"(NN)":[31],"many-to-one":[33],"mapping,":[34],"which":[35],"was":[36],"trained":[37],"from":[38],"pairs":[40],"multiple":[42],"source":[43,65],"speakers":[44],"and":[45,66,124,192],"target":[47,68,81],"speaker.":[48],"Using":[49],"NN,":[51],"design":[53],"filter":[55],"based":[56],"on":[57],"difference":[59],"spectra":[62],"to":[70,170,185],"directly":[71],"convert":[72],"waveform":[74,94],"An":[84],"advantage":[85],"method":[89],"is":[90],"that":[91,154,174],"direct":[93],"conversion":[95,177],"alleviates":[96],"quality":[98],"degradation":[99],"caused":[100],"by":[101,116],"F0":[103],"extraction":[104],"error.":[105],"To":[106],"improve":[107,193],"this":[108],"method,":[110],"use":[112],"mel-cepstral":[113],"coefficients":[114,133,149],"extracted":[115],"STRAIGHT,":[117],"high-quality":[119],"tool":[120],"analysis":[123],"synthesis.":[125],"The":[126],"higher":[127],"order":[128,166],"components":[129,169],"cepstral":[132,168],"determine":[134],"detailed":[136],"shape":[137],"spectral":[140],"envelope,":[141],"but":[142],"prediction":[144],"accuracy":[145],"high-order":[148],"might":[150],"be":[151],"worse":[152],"than":[153],"lower-order":[157],"ones.":[158],"Thus,":[159],"investigated":[161],"effect":[163],"find":[171],"condition":[173],"gave":[175],"better":[176],"quality.":[178,197],"Additionally,":[179],"exploited":[181],"dynamic":[183],"features":[184],"reduce":[186],"discontinuity":[188],"frame":[191],"converted":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-11-30T00:00:00"}