{"id":"https://openalex.org/W4396597005","doi":"https://doi.org/10.1109/access.2024.3396377","title":"Zero-Shot Voice Cloning Text-to-Speech for Dysphonia Disorder Speakers","display_name":"Zero-Shot Voice Cloning Text-to-Speech for Dysphonia Disorder Speakers","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396597005","doi":"https://doi.org/10.1109/access.2024.3396377"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3396377","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3396377","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2024.3396377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066073372","display_name":"Kurniawati Azizah","orcid":"https://orcid.org/0000-0002-3217-7025"},"institutions":[{"id":"https://openalex.org/I29617571","display_name":"University of Indonesia","ror":"https://ror.org/0116zj450","country_code":"ID","type":"education","lineage":["https://openalex.org/I29617571"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Kurniawati Azizah","raw_affiliation_strings":["Faculty of Computer Science, Universitas Indonesia, Depok, Indonesia"],"raw_orcid":"https://orcid.org/0000-0002-3217-7025","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, Universitas Indonesia, Depok, Indonesia","institution_ids":["https://openalex.org/I29617571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5066073372"],"corresponding_institution_ids":["https://openalex.org/I29617571"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":3.1646,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92297693,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"63528","last_page":"63547"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9894000291824341,"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/zero","display_name":"Zero (linguistics)","score":0.6573930382728577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5743784308433533},{"id":"https://openalex.org/keywords/voice-disorder","display_name":"Voice Disorder","score":0.5339948534965515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5043371915817261},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.4121174216270447},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.269944429397583},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2309046983718872},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11013618111610413}],"concepts":[{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6573930382728577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5743784308433533},{"id":"https://openalex.org/C2908717642","wikidata":"https://www.wikidata.org/wiki/Q4593337","display_name":"Voice Disorder","level":2,"score":0.5339948534965515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5043371915817261},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.4121174216270447},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.269944429397583},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2309046983718872},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11013618111610413},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3396377","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3396377","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d78eac9ed7424e13988c7bd9d48e80c7","is_oa":true,"landing_page_url":"https://doaj.org/article/d78eac9ed7424e13988c7bd9d48e80c7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 63528-63547 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3396377","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3396377","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1560013842","https://openalex.org/W1570629387","https://openalex.org/W1579838312","https://openalex.org/W2046056978","https://openalex.org/W2095734449","https://openalex.org/W2338517121","https://openalex.org/W2769810959","https://openalex.org/W2775336875","https://openalex.org/W2786672974","https://openalex.org/W2887171382","https://openalex.org/W2890964092","https://openalex.org/W2903853691","https://openalex.org/W2939833446","https://openalex.org/W2960427821","https://openalex.org/W2962788625","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2963945466","https://openalex.org/W2964243274","https://openalex.org/W2967957380","https://openalex.org/W2969521066","https://openalex.org/W2972394484","https://openalex.org/W2972440097","https://openalex.org/W2973032144","https://openalex.org/W2981831057","https://openalex.org/W2990124956","https://openalex.org/W3010925296","https://openalex.org/W3015707856","https://openalex.org/W3015826515","https://openalex.org/W3090254849","https://openalex.org/W3096086473","https://openalex.org/W3097547259","https://openalex.org/W3150572638","https://openalex.org/W3169905056","https://openalex.org/W4200429098","https://openalex.org/W4206596421","https://openalex.org/W4225680573","https://openalex.org/W4282960218","https://openalex.org/W4311000453","https://openalex.org/W4381708595","https://openalex.org/W6631190155","https://openalex.org/W6734815144","https://openalex.org/W6748573829","https://openalex.org/W6748816842","https://openalex.org/W6749489859","https://openalex.org/W6752888775","https://openalex.org/W6755135894","https://openalex.org/W6757322325","https://openalex.org/W6765653190","https://openalex.org/W6765987481","https://openalex.org/W6770838157","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6796464841","https://openalex.org/W6805710207","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"based":[3],"text-to-speech":[4],"(TTS)":[5],"technology":[6,75],"has":[7,77,101],"brought":[8],"advances":[9],"in":[10,30,265],"speech":[11,18,49,82,116,237,256,260,270,294,300],"synthesis":[12],"approaching":[13],"the":[14,31,43,54,60,97,105,134,139,148,197,201,204,217,221,225,235,241,266,281,288,293,299],"quality":[15,262,297],"of":[16,33,39,42,59,113,161,177,210,268,284,298],"human":[17,71],"sounds.":[19],"Zero-shot":[20],"voice":[21,46,63,124,283],"cloning":[22,64,125],"TTS":[23,65,93,126,175,179,226],"is":[24,200,248],"a":[25,36,40,208],"system":[26],"that":[27,89,196],"accepts":[28],"input":[29],"form":[32],"text":[34,155,212],"and":[35,115,152,181,183,229,259,275,296,304],"few":[37],"seconds":[38],"sample":[41],"target":[44,55],"speaker\u2019s":[45,56],"to":[47,53,96,128,146,234,240,250],"produce":[48],"sound":[50,117,261],"waves":[51],"similar":[52],"voice.":[57],"Some":[58],"latest":[61],"zero-shot":[62,92,123],"studies":[66],"still":[67,76,100],"focuses":[68],"on":[69,104,138],"normal":[70],"voices.":[72],"However,":[73],"this":[74],"limitations":[78],"for":[79],"individuals":[80],"with":[81,188,280],"disorders":[83,271],"such":[84],"as":[85,216],"dysphonia.":[86],"We":[87,142],"observe":[88,129],"our":[90,244],"baseline":[91,135,149,242],"model":[94,136,150,199,215,247,290],"applied":[95],"dysphonia":[98,140,269,285],"domain":[99,267],"poor":[102],"performance":[103,137,264],"following":[106,205],"aspects:":[107],"speaker":[108,163,169,171,189,214,218,222,231,252],"similarity,":[109],"intelligibility":[110,257,295],"or":[111,159,168,187],"clarity":[112],"speech,":[114],"quality.":[118],"This":[119],"research":[120],"develops":[121],"24":[122],"models":[127,131],"which":[130],"can":[132],"improve":[133,251],"domain.":[141],"propose":[143],"four":[144],"categories":[145],"change":[147],"architecture":[151],"setting:":[153],"input-level":[154],"sequences":[156],"(grapheme,":[157],"phoneme,":[158],"combination":[160,209],"grapheme-phoneme),":[162],"embedding":[164,172,223],"type":[165],"(speaker":[166],"encoder":[167,176,180,227],"model),":[170],"position":[173],"(at":[174],"at":[178,224],"decoder),":[182],"loss":[184,233],"function":[185],"(without":[186],"consistency":[190,232],"loss).":[191],"The":[192],"experimental":[193],"results":[194],"show":[195],"best":[198,246,289],"one":[202],"uses":[203],"configuration":[206],"settings:":[207],"grapheme-phoneme-level":[211],"sequences,":[213],"embedding,":[219],"placing":[220],"only,":[228],"adding":[230],"frame-level":[236],"loss.":[238],"Compared":[239],"model,":[243],"proposed":[245],"able":[249],"cosine":[253],"similarity":[254],"(COS),":[255],"(CER),":[258],"(MOS)":[263],"by":[272,302],"0.197,":[273],"0.55%,":[274],"0.244,":[276],"respectively.":[277,306],"When":[278],"compared":[279],"original":[282],"disorder":[286],"speakers,":[287],"also":[291],"increases":[292],"sounds":[301],"13.45%":[303],"0.22,":[305]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}