{"id":"https://openalex.org/W2920934251","doi":"https://doi.org/10.23919/apsipa.2018.8659785","title":"Hybrid Text-to-Speech for Articulation Disorders with a Small Amount of Non-Parallel Data","display_name":"Hybrid Text-to-Speech for Articulation Disorders with a Small Amount of Non-Parallel Data","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2920934251","doi":"https://doi.org/10.23919/apsipa.2018.8659785","mag":"2920934251"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659785","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5013118187","display_name":"Ryuka Nanzaka","orcid":null},"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":true,"raw_author_name":"Ryuka Nanzaka","raw_affiliation_strings":["Kobe University, Japan"],"affiliations":[{"raw_affiliation_string":"Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"last","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, Japan"],"affiliations":[{"raw_affiliation_string":"Kobe University, Japan","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013118187"],"corresponding_institution_ids":["https://openalex.org/I65837984"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62094835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1761","last_page":"1765"},"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":0.9995999932289124,"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/T11309","display_name":"Music and Audio Processing","score":0.9973000288009644,"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/articulation","display_name":"Articulation (sociology)","score":0.9024909138679504},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7162114381790161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6553795337677002},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6277640461921692},{"id":"https://openalex.org/keywords/speech-disorder","display_name":"Speech disorder","score":0.5294805765151978},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5012657642364502},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41500720381736755},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.4146643579006195},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27562469244003296},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11500787734985352}],"concepts":[{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.9024909138679504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7162114381790161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6553795337677002},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6277640461921692},{"id":"https://openalex.org/C2779642007","wikidata":"https://www.wikidata.org/wiki/Q1282114","display_name":"Speech disorder","level":2,"score":0.5294805765151978},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5012657642364502},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41500720381736755},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.4146643579006195},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27562469244003296},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11500787734985352},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659785","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659785","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W187033940","https://openalex.org/W1987992317","https://openalex.org/W2000513720","https://openalex.org/W2005768155","https://openalex.org/W2049686551","https://openalex.org/W2056661291","https://openalex.org/W2102003408","https://openalex.org/W2120605154","https://openalex.org/W2154920538","https://openalex.org/W2294797155","https://openalex.org/W2295316334","https://openalex.org/W2475998840","https://openalex.org/W2576309025","https://openalex.org/W2748881396","https://openalex.org/W2774848319","https://openalex.org/W2964341837","https://openalex.org/W4293398859","https://openalex.org/W6607663849","https://openalex.org/W6675380101","https://openalex.org/W6696843773","https://openalex.org/W6730095352"],"related_works":["https://openalex.org/W1544536563","https://openalex.org/W4280646740","https://openalex.org/W2060836468","https://openalex.org/W2608841979","https://openalex.org/W2004780548","https://openalex.org/W2748448327","https://openalex.org/W2772709568","https://openalex.org/W2088222388","https://openalex.org/W2786684668","https://openalex.org/W1494715773"],"abstract_inverted_index":{"Conventional":[0],"approaches":[1],"to":[2,27,81,152,210],"statistical":[3],"parametric":[4],"speech":[5,13,33,102,116,166],"synthesis":[6,103,110],"usually":[7],"require":[8,190],"a":[9,29,56,60,70,75,115,119,124,131,155,162,169,182],"large":[10,30,125],"amount":[11,31,126,164],"of":[12,32,69,127,130,147,154,165,168,215],"data.":[14],"But":[15],"it":[16],"is":[17,111,135,141,175,193],"very":[18],"difficult":[19],"for":[20,59,113,143,178,195],"persons":[21],"with":[22,62,77,157,171],"articulation":[23,64,79,93,159,173],"disorders,":[24],"in":[25,213],"particular,":[26],"utter":[28],"data,":[34],"and":[35,74,105,219],"their":[36],"utterances":[37],"are":[38,208],"often":[39],"unstable":[40],"or":[41],"unclear":[42],"so":[43],"that":[44,153,187,201],"we":[45,54],"cannot":[46],"understand":[47],"what":[48],"they":[49],"say.":[50],"In":[51],"this":[52],"paper,":[53],"propose":[55],"hybrid":[57],"approach":[58],"person":[61,73,76,134,151,156,170],"an":[63,78,83,92,158,172],"disorder,":[65,160],"using":[66,205],"two":[67,98],"models":[68],"physically":[71,120,132,149],"unimpaired":[72,121,133,150],"disorder":[80,174],"generate":[82],"intelligible":[84],"voice":[85,106,138,146],"while":[86],"preserving":[87],"the":[88,101,145,148,202,211],"speaker's":[89],"individuality":[90],"(with":[91],"disorder).":[94],"Our":[95],"method":[96,207],"has":[97],"processes":[99],"-":[100],"part":[104],"conversion":[107,139],"part.":[108],"Speech":[109],"employed":[112,142,194],"obtaining":[114],"signal":[117],"(of":[118],"person),":[122],"where":[123,161],"training":[128,179],"data":[129,167,192],"used.":[136],"Then,":[137],"(VC)":[140],"converting":[144],"small":[163],"only":[176],"used":[177],"VC.":[180,196],"Also,":[181],"cycle-consistent":[183],"adversarial":[184],"network":[185],"(CycleGAN)":[186],"does":[188],"not":[189],"parallel":[191],"An":[197],"objective":[198],"evaluation":[199],"showed":[200],"mel-cepstrum":[203],"obtained":[204],"our":[206],"close":[209],"target":[212],"terms":[214],"global":[216],"variance":[217],"(GV)":[218],"modulation":[220],"spectrum":[221],"(MS).":[222]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}