{"id":"https://openalex.org/W4406266750","doi":"https://doi.org/10.1109/gcce62371.2024.10760396","title":"Training of VITS Model Reflecting the Duration of a Physically Unimpaired Speaker for a Text-to-speech System for a Person with a Stutter","display_name":"Training of VITS Model Reflecting the Duration of a Physically Unimpaired Speaker for a Text-to-speech System for a Person with a Stutter","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4406266750","doi":"https://doi.org/10.1109/gcce62371.2024.10760396"},"language":"en","primary_location":{"id":"doi:10.1109/gcce62371.2024.10760396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","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/A5115842228","display_name":"Ryo Nagakubo","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":false,"raw_author_name":"Ryo Nagakubo","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Kobe,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Kobe,Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085108313","display_name":"Haruki Yamashita","orcid":"https://orcid.org/0009-0001-8553-9317"},"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":"Haruki Yamashita","raw_affiliation_strings":["Kobe University,Graduate School of System Informatics,Kobe,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Kobe,Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"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,Kobe,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Kobe,Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115842229","display_name":"Misuzu Yasui","orcid":null},"institutions":[{"id":"https://openalex.org/I37596208","display_name":"Osaka University of Human Sciences","ror":"https://ror.org/05cp38y47","country_code":"JP","type":"education","lineage":["https://openalex.org/I37596208"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Misuzu Yasui","raw_affiliation_strings":["Osaka University of Human Sciences,Faculty of Health Sciences,Osaka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University of Human Sciences,Faculty of Health Sciences,Osaka,Japan","institution_ids":["https://openalex.org/I37596208"]}]},{"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,Graduate School of System Informatics,Kobe,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kobe University,Graduate School of System Informatics,Kobe,Japan","institution_ids":["https://openalex.org/I65837984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"422"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/3203","display_name":"Clinical Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7160667777061462},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7143268585205078},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6192554235458374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36466842889785767},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33618760108947754},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06797859072685242},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05873015522956848}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7160667777061462},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7143268585205078},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6192554235458374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36466842889785767},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33618760108947754},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06797859072685242},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05873015522956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce62371.2024.10760396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295"],"abstract_inverted_index":{"In":[0],"this":[1,17],"study,":[2],"we":[3,57],"propose":[4,58],"a":[5,10,13,29,39,52,59,64,73],"text-to-speech":[6],"(TTS)":[7],"system":[8,41],"for":[9,62],"person":[11],"with":[12,16,47],"stutter.":[14],"Those":[15],"speech":[18,23,46,90,98],"disorder":[19],"have":[20],"less":[21],"fluent":[22,45],"than":[24],"physically":[25,74],"unimpaired":[26,75],"speakers.":[27],"As":[28],"result,":[30],"it":[31],"causes":[32],"difficulty":[33],"in":[34,88],"smooth":[35],"communication.":[36],"To":[37],"create":[38],"TTS":[40,65],"capable":[42],"of":[43,51,72],"synthesizing":[44],"the":[48,69,89,96,102],"voice":[49],"individuality":[50],"target":[53],"speaker":[54],"who":[55],"stutters,":[56],"training":[60],"method":[61,84],"VITS,":[63],"system,":[66],"that":[67,81],"reflects":[68],"phoneme":[70],"duration":[71,99],"speaker.":[76],"Our":[77],"experimental":[78],"results":[79],"show":[80],"our":[82],"proposed":[83],"removes":[85],"long":[86],"pauses":[87],"caused":[91],"by":[92],"stuttering":[93],"and":[94],"shortens":[95],"total":[97],"compared":[100],"to":[101],"conventional":[103],"method.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}