{"id":"https://openalex.org/W3160618567","doi":"https://doi.org/10.1109/icassp39728.2021.9414136","title":"High-Intelligibility Speech Synthesis for Dysarthric Speakers with LPCNet-Based TTS and CycleVAE-Based VC","display_name":"High-Intelligibility Speech Synthesis for Dysarthric Speakers with LPCNet-Based TTS and CycleVAE-Based VC","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160618567","doi":"https://doi.org/10.1109/icassp39728.2021.9414136","mag":"3160618567"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082668383","display_name":"Keisuke Matsubara","orcid":"https://orcid.org/0000-0002-2935-668X"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Matsubara","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Japan","National Institute of Information and Communications Technology, Japan","Graduate School of System Informatics, Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Japan","Graduate School of System Informatics, Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Japan","Graduate School of System Informatics, Kobe University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Information Technology Center,Japan","National Institute of Information and Communications Technology, Japan","Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109350986","display_name":"Yoshinori Shiga","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshinori Shiga","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7058","last_page":"7062"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9983999729156494,"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":0.9901999831199646,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.8490980863571167},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.8356982469558716},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6986345052719116},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6330459117889404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.611330509185791},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.535315990447998},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5109761953353882},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.25629812479019165},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1685982644557953}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8490980863571167},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.8356982469558716},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6986345052719116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6330459117889404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.611330509185791},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.535315990447998},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5109761953353882},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.25629812479019165},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1685982644557953},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W1965255698","https://openalex.org/W2005768155","https://openalex.org/W2011378162","https://openalex.org/W2111284386","https://openalex.org/W2120605154","https://openalex.org/W2142300631","https://openalex.org/W2168510624","https://openalex.org/W2295316334","https://openalex.org/W2471520273","https://openalex.org/W2898786057","https://openalex.org/W2903739847","https://openalex.org/W2920934251","https://openalex.org/W2937579788","https://openalex.org/W2946555236","https://openalex.org/W2963091184","https://openalex.org/W2963403868","https://openalex.org/W2963945466","https://openalex.org/W2972544500","https://openalex.org/W2972689158","https://openalex.org/W3012461590","https://openalex.org/W3015338123","https://openalex.org/W3015586278","https://openalex.org/W3016160783","https://openalex.org/W3081800019","https://openalex.org/W3082130377","https://openalex.org/W3092246895","https://openalex.org/W3117914007","https://openalex.org/W4385245566","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6840412704"],"related_works":["https://openalex.org/W2084983866","https://openalex.org/W3012459429","https://openalex.org/W3015238377","https://openalex.org/W2091380405","https://openalex.org/W2027206961","https://openalex.org/W4312547701","https://openalex.org/W2081214229","https://openalex.org/W2890040947","https://openalex.org/W3022666696","https://openalex.org/W2909404091"],"abstract_inverted_index":{"This":[0,96],"paper":[1],"presents":[2],"a":[3,48,67,89],"high-intelligibility":[4],"speech":[5,54,87],"synthesis":[6],"method":[7,49,79,115],"for":[8,39,50],"persons":[9],"with":[10],"dysarthria":[11],"caused":[12],"by":[13,62,93],"athetoid":[14,28],"cerebral":[15],"palsy.":[16],"The":[17],"muscular":[18],"control":[19],"of":[20,26,59,88,106,121,130],"such":[21],"speakers":[22,61],"is":[23,33,98],"unstable":[24],"because":[25],"their":[27,31],"symptoms,":[29],"and":[30,66,101],"pronunciation":[32],"unclear,":[34],"which":[35],"makes":[36],"it":[37],"difficult":[38],"them":[40],"to":[41,85],"communicate.":[42],"In":[43],"this":[44,78],"paper,":[45],"we":[46,110],"present":[47],"generating":[51],"highly":[52],"intelligible":[53],"that":[55,112],"preserves":[56],"the":[57,75,81,86,104,113,119,122,128,131],"individuality":[58,84,120],"dysarthric":[60,76,82,124],"combining":[63],"Transformer-TTS,":[64],"CycleVAE-VC,":[65],"LPCNet":[68],"vocoder.":[69],"Rather":[70],"than":[71],"repairing":[72],"prosody":[73],"from":[74],"speech,":[77],"transfers":[80],"speaker\u2019s":[83],"healthy":[90],"person":[91],"generated":[92],"TTS":[94],"synthesis.":[95],"task":[97],"both":[99],"important":[100],"challenging.":[102],"From":[103],"results":[105],"our":[107],"evaluation":[108],"experiments,":[109],"confirmed":[111],"proposed":[114],"can":[116],"partially":[117],"transfer":[118],"target":[123],"speaker":[125],"while":[126],"maintaining":[127],"intelligibility":[129],"source":[132],"speech.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}