{"id":"https://openalex.org/W2770751809","doi":"https://doi.org/10.1109/taslp.2017.2753583","title":"Articulatory Controllable Speech Modification Based on Statistical Inversion and Production Mappings","display_name":"Articulatory Controllable Speech Modification Based on Statistical Inversion and Production Mappings","publication_year":2017,"publication_date":"2017-11-23","ids":{"openalex":"https://openalex.org/W2770751809","doi":"https://doi.org/10.1109/taslp.2017.2753583","mag":"2770751809"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2753583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2753583","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nagoya.repo.nii.ac.jp/records/25726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.1963,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.85055269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"25","issue":"12","first_page":"2337","last_page":"2350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8401273488998413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7201619148254395},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6649428606033325},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5822043418884277},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5626923441886902},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5087898373603821},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5010874271392822},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.4569888114929199},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20675697922706604}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8401273488998413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7201619148254395},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6649428606033325},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5822043418884277},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5626923441886902},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5087898373603821},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5010874271392822},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.4569888114929199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20675697922706604},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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":2,"locations":[{"id":"doi:10.1109/taslp.2017.2753583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2753583","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01152:0001468841","is_oa":true,"landing_page_url":"https://nagoya.repo.nii.ac.jp/records/25726","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01152:0001468841","is_oa":true,"landing_page_url":"https://nagoya.repo.nii.ac.jp/records/25726","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2939355294","display_name":null,"funder_award_id":"16J10726","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G3497787681","display_name":null,"funder_award_id":"JPMJPR1657","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"id":"https://openalex.org/G6056306111","display_name":null,"funder_award_id":"17H01763","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G6466568207","display_name":"Development of fundamental technology for speech and sound event processing based on complementary use of air- and body-conducted sound signals","funder_award_id":"17H01763","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"},{"id":"https://openalex.org/F4320320907","display_name":"Japan Science and Technology Corporation","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W46785905","https://openalex.org/W123135133","https://openalex.org/W200485868","https://openalex.org/W205886270","https://openalex.org/W208520372","https://openalex.org/W221422375","https://openalex.org/W275819404","https://openalex.org/W1488772215","https://openalex.org/W1552319954","https://openalex.org/W1557859345","https://openalex.org/W1558306184","https://openalex.org/W1564657563","https://openalex.org/W1588266896","https://openalex.org/W1589867908","https://openalex.org/W1607802755","https://openalex.org/W1751815199","https://openalex.org/W1935012542","https://openalex.org/W1977591085","https://openalex.org/W1982854652","https://openalex.org/W1986174057","https://openalex.org/W1990394889","https://openalex.org/W1995387737","https://openalex.org/W2006775235","https://openalex.org/W2013317861","https://openalex.org/W2023407680","https://openalex.org/W2034829178","https://openalex.org/W2043202047","https://openalex.org/W2049686551","https://openalex.org/W2052382192","https://openalex.org/W2054764113","https://openalex.org/W2066119955","https://openalex.org/W2079402412","https://openalex.org/W2110164509","https://openalex.org/W2116082100","https://openalex.org/W2120605154","https://openalex.org/W2134539847","https://openalex.org/W2141684970","https://openalex.org/W2143493821","https://openalex.org/W2145892079","https://openalex.org/W2155077107","https://openalex.org/W2156142001","https://openalex.org/W2157555349","https://openalex.org/W2231075402","https://openalex.org/W2293049663","https://openalex.org/W2293872531","https://openalex.org/W2294038178","https://openalex.org/W2296654356","https://openalex.org/W2395052932","https://openalex.org/W2401186958","https://openalex.org/W2401296648","https://openalex.org/W2401299519","https://openalex.org/W2406009389","https://openalex.org/W2509129594","https://openalex.org/W2533081766","https://openalex.org/W4206319965","https://openalex.org/W4245284779","https://openalex.org/W4362702728","https://openalex.org/W6608480465","https://openalex.org/W6609917237","https://openalex.org/W6635216677","https://openalex.org/W6635242571","https://openalex.org/W6680683932","https://openalex.org/W6696994987","https://openalex.org/W6697024540","https://openalex.org/W6711753470","https://openalex.org/W6712902469","https://openalex.org/W6713226901","https://openalex.org/W6714339243"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,28,90,109],"present":[4],"an":[5,21,61,129],"innovative":[6],"way":[7],"of":[8,47,54,60,67,77,86,113,121,126,150,190,197,207,220,228,236],"utilizing":[9],"the":[10,48,52,55,68,84,111,134,148,172,195,198,205,218,221,234],"natural":[11,188],"relationship":[12],"between":[13],"speech":[14,24,63,107,131,209],"sounds":[15,232],"and":[16,34,51,79,159,216],"articulatory":[17,22,70,87,96,169,176,192,238],"movements":[18,71],"by":[19,98,117,155,178,225],"developing":[20],"controllable":[23],"modification":[25,46,124,201],"system.":[26],"Specifically,":[27],"employ":[29],"statistical":[30],"acoustic-to-articulatory":[31],"inversion":[32,78,158],"mapping":[33,37,166],"articulatory-to-acoustic":[35],"production":[36,80,160,165],"based":[38],"on":[39],"a":[40,75,92],"Gaussian":[41],"mixture":[42],"model,":[43],"allowing":[44],"flexible":[45],"model":[49],"parameters":[50,97,152,177],"independence":[53],"text":[56],"input":[57,62,130],"features.":[58],"Modification":[59],"signal":[64,132],"through":[65,74,233],"manipulation":[66,235],"unobserved":[69],"is":[72,153,223],"achievable":[73],"sequence":[76],"mappings.":[81],"To":[82],"ensure":[83],"naturalness":[85],"movement":[88],"trajectories,":[89],"introduce":[91],"method":[93,173,202],"for":[94,163,174],"manipulating":[95,175],"considering":[99,179],"their":[100,180],"intercorrelation.":[101],"Moreover,":[102],"to":[103,185],"generate":[104,186],"high-quality":[105],"modified":[106,191,208,230],"sounds,":[108,210],"avoid":[110],"use":[112],"vocoder-based":[114],"excitation":[115],"generation":[116],"presenting":[118],"several":[119],"implementations":[120,196],"direct":[122,199],"waveform":[123,200],"capable":[125],"directly":[127],"filtering":[128],"using":[133,156,167],"differences":[135],"in":[136,147],"spectral":[137,151],"parameters.":[138],"The":[139],"experimental":[140],"results":[141],"demonstrate":[142],"that:":[143],"1)":[144],"higher":[145],"accuracy":[146],"estimation":[149],"achieved":[154],"sequential":[157],"mappings":[161],"than":[162],"conventional":[164],"measured":[168],"parameters,":[170],"2)":[171],"intercorrelation":[181],"makes":[182],"it":[183],"possible":[184],"more":[187],"trajectories":[189],"movements;":[193],"3)":[194],"significantly":[203],"improve":[204],"quality":[206],"even":[211],"under":[212],"varying":[213],"speaking":[214],"conditions;":[215],"4)":[217],"controllability":[219],"system":[222],"ensured":[224],"its":[226],"capability":[227],"producing":[229],"vowel":[231],"appropriate":[237],"configurations.":[239]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}