{"id":"https://openalex.org/W7135409970","doi":"https://doi.org/10.5715/jnlp.33.186","title":"Which One Sounds More Human-like? \u2014Comparison of Synthetic Speech Trained on Japanese Daily Conversational Data with and without Disfluency","display_name":"Which One Sounds More Human-like? \u2014Comparison of Synthetic Speech Trained on Japanese Daily Conversational Data with and without Disfluency","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7135409970","doi":"https://doi.org/10.5715/jnlp.33.186"},"language":"en","primary_location":{"id":"doi:10.5715/jnlp.33.186","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.186","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/1/33_186/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/jnlp/33/1/33_186/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027405356","display_name":"Akiko Mokhtari","orcid":null},"institutions":[{"id":"https://openalex.org/I63216439","display_name":"Toyama Prefectural University","ror":"https://ror.org/03xgh2v50","country_code":"JP","type":"education","lineage":["https://openalex.org/I63216439"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akiko Mokhtari","raw_affiliation_strings":["Toyama Prefectural University"],"affiliations":[{"raw_affiliation_string":"Toyama Prefectural University","institution_ids":["https://openalex.org/I63216439"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050990632","display_name":"Hiroaki Hatano","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":"Hiroaki Hatano","raw_affiliation_strings":["Kobe University"],"affiliations":[{"raw_affiliation_string":"Kobe University","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108655697","display_name":"Jun Arai","orcid":null},"institutions":[{"id":"https://openalex.org/I206011266","display_name":"Kwansei Gakuin University","ror":"https://ror.org/02qf2tx24","country_code":"JP","type":"education","lineage":["https://openalex.org/I206011266"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Arai","raw_affiliation_strings":["Kwansei Gakuin University"],"affiliations":[{"raw_affiliation_string":"Kwansei Gakuin University","institution_ids":["https://openalex.org/I206011266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108471155","display_name":"Nick Campbell","orcid":null},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]},{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Nick Campbell","raw_affiliation_strings":["The University of Dublin"],"affiliations":[{"raw_affiliation_string":"The University of Dublin","institution_ids":["https://openalex.org/I100930933","https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043519277","display_name":"Toshiyuki Sadanobu","orcid":"https://orcid.org/0000-0002-4249-3355"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiyuki Sadanobu","raw_affiliation_strings":["Kyoto University"],"affiliations":[{"raw_affiliation_string":"Kyoto University","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027405356"],"corresponding_institution_ids":["https://openalex.org/I63216439"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62766698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"1","first_page":"186","last_page":"206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.24940000474452972,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T10403","display_name":"Phonetics and Phonology Research","score":0.24940000474452972,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.23180000483989716,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12684","display_name":"Stuttering Research and Treatment","score":0.04450000077486038,"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/feature","display_name":"Feature (linguistics)","score":0.25029999017715454},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.24660000205039978},{"id":"https://openalex.org/keywords/phonation","display_name":"Phonation","score":0.23440000414848328}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4514999985694885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42089998722076416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33959999680519104},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31029999256134033},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.24660000205039978},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.23440000414848328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5715/jnlp.33.186","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.186","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/1/33_186/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5715/jnlp.33.186","is_oa":true,"landing_page_url":"https://doi.org/10.5715/jnlp.33.186","pdf_url":"https://www.jstage.jst.go.jp/article/jnlp/33/1/33_186/_pdf","source":{"id":"https://openalex.org/S4210212357","display_name":"Journal of Natural Language Processing","issn_l":"1340-7619","issn":["1340-7619","2185-8314"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Natural Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5912172794342041,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G12401395","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G6267471473","display_name":null,"funder_award_id":"Grant-in-Aid","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G7599130655","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7135409970.pdf","grobid_xml":"https://content.openalex.org/works/W7135409970.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"real-world":[1],"conversational":[2,54,89],"speech":[3,19,84,103,136],"is":[4,9,175],"full":[5],"of":[6,33,46,75,104,131,155,161,167],"disfluencies,":[7,36],"it":[8],"vital":[10],"to":[11,16,40,157,192],"include":[12],"them":[13],"when":[14],"aiming":[15],"create":[17],"a":[18,92,127],"synthesis":[20,85],"that":[21,126,173],"reflects":[22],"real":[23],"human":[24],"interactions.":[25],"While":[26],"recent":[27],"studies":[28],"have":[29],"developed":[30],"models":[31],"capable":[32],"automatically":[34],"inserting":[35],"this":[37],"study":[38],"aims":[39],"clarify":[41],"how":[42],"five":[43],"specific":[44,193],"types":[45],"manually":[47],"inserted":[48],"disfluencies":[49,112],"commonly":[50],"observed":[51],"in":[52,96,190],"Japanese":[53,94],"speech\u2014fillers,":[55],"word-internal":[56],"prolongations,":[57],"phrase-final":[58,62,67],"abrupt":[59,63],"rising":[60],"intonation,":[61,65],"rising-and-falling":[64],"and":[66,110,113,148,153,182],"copulas":[68],"with":[69,109],"sentence-final":[70],"particles\u2014affect":[71],"the":[72,97,105,115,143,146,149,165,168,179,183],"perceived":[73],"human-likeness":[74],"synthetic":[76,135],"speech.":[77],"First,":[78],"we":[79],"train":[80],"an":[81,176],"existing":[82],"AI-based":[83],"system":[86],"using":[87],"daily":[88],"data":[90],"from":[91],"female":[93],"speaker":[95],"Kinki":[98],"dialect.":[99],"We":[100,140],"then":[101],"synthesised":[102],"same":[106],"linguistic":[107],"content":[108],"without":[111],"asked":[114],"survey":[116],"respondents":[117,132],"which":[118],"sample":[119],"sounded":[120],"more":[121,138],"human-like.":[122,139],"The":[123,170],"results":[124,171],"showed":[125],"significantly":[128],"higher":[129],"percentage":[130],"evaluated":[133],"disfluent":[134],"as":[137],"also":[141],"analysed":[142],"relationship":[144],"between":[145,178],"answers":[147,181],"respondents'":[150,180],"gender,":[151],"age,":[152],"place":[154],"upbringing":[156],"investigate":[158],"whether":[159],"any":[160],"these":[162],"attributes":[163],"influenced":[164],"tendency":[166],"answers.":[169],"suggest":[172],"there":[174],"association":[177],"regions":[184],"where":[185],"they":[186],"grew":[187],"up,":[188],"particularly":[189],"response":[191],"stimulus":[194],"sounds.":[195]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2026-03-15T00:00:00"}
