{"id":"https://openalex.org/W2052871313","doi":"https://doi.org/10.1109/globalsip.2014.7032186","title":"Augmented speech production based on real-time statistical voice conversion","display_name":"Augmented speech production based on real-time statistical voice conversion","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2052871313","doi":"https://doi.org/10.1109/globalsip.2014.7032186","mag":"2052871313"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2014.7032186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Nara, JAPAN","Graduate School of Information Science, Nara Institute of Science and Technology Takayama 8916-5, Ikoma, Nara, 630-0192 Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Nara, JAPAN","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology Takayama 8916-5, Ikoma, Nara, 630-0192 Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078330211"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.8462666,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"20","issue":null,"first_page":"592","last_page":"596"},"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":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.991100013256073,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8399081230163574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7751862406730652},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7320654392242432},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5731488466262817},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5611997842788696},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5311635136604309},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5197843909263611},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4605426490306854},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.4533322751522064},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.42061564326286316}],"concepts":[{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8399081230163574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751862406730652},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7320654392242432},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5731488466262817},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5611997842788696},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5311635136604309},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5197843909263611},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4605426490306854},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.4533322751522064},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.42061564326286316},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2014.7032186","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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":45,"referenced_works":["https://openalex.org/W1482298176","https://openalex.org/W1581272224","https://openalex.org/W1964420823","https://openalex.org/W1974745215","https://openalex.org/W1977362459","https://openalex.org/W1982854652","https://openalex.org/W1984905644","https://openalex.org/W1987992317","https://openalex.org/W1991590998","https://openalex.org/W2002342963","https://openalex.org/W2007023536","https://openalex.org/W2008120082","https://openalex.org/W2013996527","https://openalex.org/W2023694213","https://openalex.org/W2035962301","https://openalex.org/W2039800941","https://openalex.org/W2048646122","https://openalex.org/W2049686551","https://openalex.org/W2056852181","https://openalex.org/W2077865492","https://openalex.org/W2086525417","https://openalex.org/W2086796102","https://openalex.org/W2091456738","https://openalex.org/W2097873655","https://openalex.org/W2100969003","https://openalex.org/W2106554350","https://openalex.org/W2111284386","https://openalex.org/W2114543868","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2123003832","https://openalex.org/W2127520494","https://openalex.org/W2129142580","https://openalex.org/W2148846882","https://openalex.org/W2154920538","https://openalex.org/W2156142001","https://openalex.org/W2161135987","https://openalex.org/W2161736993","https://openalex.org/W2162295204","https://openalex.org/W2165108269","https://openalex.org/W2179117922","https://openalex.org/W2293526996","https://openalex.org/W2295147651","https://openalex.org/W2406654659","https://openalex.org/W2943553228"],"related_works":["https://openalex.org/W2334129531","https://openalex.org/W2515097069","https://openalex.org/W642007152","https://openalex.org/W4300049944","https://openalex.org/W1978136968","https://openalex.org/W4253660971","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W596245619","https://openalex.org/W2343205865"],"abstract_inverted_index":{"In":[0],"human-to-human":[1,188],"speech":[2,35,44,60,155,189,195],"communication,":[3,190,196],"various":[4,135],"barriers":[5,29],"are":[6],"caused":[7],"by":[8,159],"some":[9,180],"constraints,":[10],"such":[11,191],"as":[12,46,192],"physical":[13],"constraints":[14,20],"causing":[15],"vocal":[16],"disorders":[17],"and":[18,161,197],"environmental":[19],"making":[21],"it":[22,129],"hard":[23],"to":[24,65,81,121,133,171,186],"produce":[25,43],"intelligible":[26],"speech.":[27],"These":[28],"would":[30],"be":[31],"overcome":[32],"if":[33],"our":[34],"production":[36],"was":[37,104],"augmented":[38],"so":[39],"that":[40,124,148,165],"we":[41,47,68],"could":[42],"sounds":[45],"want":[48,69],"beyond":[49,137],"these":[50],"constraints.":[51],"Voice":[52],"conversion":[53,95,146,169,174],"(VC)":[54],"is":[55,83,89,149],"a":[56,93,98,118,144],"technique":[57,103],"for":[58],"modifying":[59],"acoustics,":[61],"converting":[62],"non-/para-linguistic":[63],"information":[64],"any":[66],"form":[67],"while":[70],"preserving":[71],"the":[72,77,108,115],"linguistic":[73],"content.":[74],"One":[75],"of":[76,91,110,117,125,151,182],"most":[78],"popular":[79],"approaches":[80],"VC":[82,184],"based":[84],"on":[85],"statistical":[86],"processing,":[87],"which":[88,113],"capable":[90,150],"extracting":[92],"complex":[94],"function":[96],"in":[97,107],"data-driven":[99],"manner.":[100],"Although":[101],"this":[102,167,177],"originally":[105],"studied":[106],"context":[109],"speaker":[111,120,138],"conversion,":[112],"converts":[114],"voice":[116,198],"certain":[119],"sound":[122],"like":[123],"another":[126],"specific":[127],"speaker,":[128],"has":[130],"great":[131],"potential":[132],"achieve":[134,172],"applications":[136,185],"conversion.":[139],"This":[140],"paper":[141,178],"briefly":[142],"reviews":[143],"trajectory-based":[145,168],"method":[147,170],"effectively":[152],"reproducing":[153],"natural":[154],"parameter":[156],"trajectories":[157],"utterance":[158,160],"highlights":[162],"several":[163],"techniques":[164],"extend":[166],"real-time":[173,183],"processing.":[175],"Finally":[176],"shows":[179],"examples":[181],"enhance":[187],"speaking-aid,":[193],"silent":[194],"changer/vocal":[199],"effector.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}