{"id":"https://openalex.org/W4402402589","doi":"https://doi.org/10.1109/ialp63756.2024.10661160","title":"Two-stage and Self-supervised Voice Conversion for Zero-Shot Dysarthric Speech Reconstruction","display_name":"Two-stage and Self-supervised Voice Conversion for Zero-Shot Dysarthric Speech Reconstruction","publication_year":2024,"publication_date":"2024-08-04","ids":{"openalex":"https://openalex.org/W4402402589","doi":"https://doi.org/10.1109/ialp63756.2024.10661160"},"language":"en","primary_location":{"id":"doi:10.1109/ialp63756.2024.10661160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp63756.2024.10661160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","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/A5032176468","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0003-4346-9565"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Liu","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768194","display_name":"Yueqian Lin","orcid":"https://orcid.org/0000-0003-1473-8981"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueqian Lin","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101791717","display_name":"Hui Bu","orcid":"https://orcid.org/0000-0002-5883-1195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Bu","raw_affiliation_strings":["AISHELL Foundation,Beijing,China"],"affiliations":[{"raw_affiliation_string":"AISHELL Foundation,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351421","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-4073-0273"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan,China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5032176468"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":2.9009,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92034079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9994999766349792,"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":0.9962000250816345,"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/speech-recognition","display_name":"Speech recognition","score":0.703683078289032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6067612767219543},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5051770806312561},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.48554274439811707},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4482007920742035},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42209959030151367},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11616083979606628}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.703683078289032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067612767219543},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5051770806312561},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.48554274439811707},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4482007920742035},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42209959030151367},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11616083979606628},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp63756.2024.10661160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp63756.2024.10661160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","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":31,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2005768155","https://openalex.org/W2011378162","https://openalex.org/W2077801020","https://openalex.org/W2124641009","https://openalex.org/W2142300631","https://openalex.org/W2194775991","https://openalex.org/W2562848127","https://openalex.org/W2576309025","https://openalex.org/W2739879705","https://openalex.org/W2748881396","https://openalex.org/W2787748320","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2963609956","https://openalex.org/W2969985801","https://openalex.org/W2972689158","https://openalex.org/W3015707856","https://openalex.org/W3092028330","https://openalex.org/W3197478142","https://openalex.org/W3209984917","https://openalex.org/W4224929761","https://openalex.org/W4305009700","https://openalex.org/W4385823432","https://openalex.org/W4391021679","https://openalex.org/W4392910324","https://openalex.org/W6638523607","https://openalex.org/W6729138736","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6846187620"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W127416991"],"abstract_inverted_index":{"Dysarthria":[0,142],"is":[1],"a":[2,55,73,78,178],"motor":[3],"speech":[4,27,36,94,98,122,163],"disorder":[5],"commonly":[6],"associated":[7],"with":[8,22,51,96],"conditions":[9],"such":[10],"as":[11],"cerebral":[12],"palsy,":[13],"Parkinson\u2019s":[14],"disease,":[15],"amyotrophic":[16],"lateral":[17],"sclerosis,":[18],"and":[19,38,41,115,130,165,170],"stroke.":[20],"Individuals":[21],"dysarthria":[23],"typically":[24],"exhibit":[25],"significant":[26],"difficulties,":[28],"including":[29],"imprecise":[30],"articulation,":[31],"lack":[32],"of":[33,64,99,120,138,160],"fluency,":[34],"slow":[35],"rate,":[37],"decreased":[39],"volume":[40],"clarity,":[42],"which":[43],"can":[44,154,185],"hinder":[45],"their":[46],"ability":[47],"to":[48,60,81,110],"communicate":[49],"effectively":[50],"others.":[52],"We":[53],"propose":[54],"two-stage":[56],"Voice":[57],"Conversion":[58],"method":[59,176],"enhance":[61],"the":[62,68,84,92,100,104,112,117,121,125,136,139,151],"reconstruction":[63],"dysarthric":[65,85,93],"speech.":[66,86],"In":[67,87,103],"first":[69,126],"stage,":[70,89,106],"we":[71,90,107],"develop":[72],"KNN-VC":[74],"approach":[75,153],"based":[76],"on":[77,135],"same-gender-retrieval":[79],"strategy":[80],"preliminarily":[82],"repair":[83],"this":[88],"match":[91],"only":[95],"normal":[97],"same":[101],"gender.":[102],"second":[105],"adapt":[108],"so-vits-svc":[109],"restore":[111],"speaker\u2019s":[113],"timbre":[114],"improve":[116],"sound":[118],"quality":[119],"repaired":[123],"in":[124,158],"stage.":[127],"Both":[128],"objective":[129],"subjective":[131],"evaluations":[132,172],"were":[133],"conducted":[134],"dataset":[137],"Low":[140],"Resource":[141],"Wake-Up":[143],"Word":[144],"Spotting":[145],"Challenge":[146],"(LRDWWS":[147],"Challenge)":[148],"shows":[149],"that":[150],"proposed":[152],"achieve":[155],"some":[156],"improvements":[157],"terms":[159],"speaker":[161],"similarity,":[162],"intelligibility":[164],"naturalness":[166],"for":[167],"unknown":[168],"speakers,":[169],"these":[171],"also":[173],"show":[174],"our":[175],"has":[177],"good":[179],"Zero-shot":[180],"performance.":[181],"Our":[182],"audio":[183],"samples":[184],"be":[186],"accessed":[187],"online":[188],"<sup":[189],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}