{"id":"https://openalex.org/W3113499882","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295020","title":"Towards Speech Entrainment: Considering ASR Information in Speaking Rate Variation of TTS Waveform Generation","display_name":"Towards Speech Entrainment: Considering ASR Information in Speaking Rate Variation of TTS Waveform Generation","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3113499882","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295020","mag":"3113499882"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda50338.2020.9295020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5014032810","display_name":"Mayuko Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mayuko Okamoto","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology RIKEN, Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology RIKEN, Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology RIKEN, Advanced Intelligence Project AIP, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology RIKEN, Advanced Intelligence Project AIP, Japan","institution_ids":["https://openalex.org/I4210126580","https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014032810"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17267559,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"139","last_page":"144"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7721048593521118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6736799478530884},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6057074666023254},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5494644641876221},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5203815698623657},{"id":"https://openalex.org/keywords/entrainment","display_name":"Entrainment (biomusicology)","score":0.5174389481544495},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47046029567718506},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.43660491704940796},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.4159262180328369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3625261187553406},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35936439037323},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.13826322555541992},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1005171537399292},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07048633694648743},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07011598348617554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721048593521118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6736799478530884},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6057074666023254},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5494644641876221},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5203815698623657},{"id":"https://openalex.org/C139992725","wikidata":"https://www.wikidata.org/wiki/Q5380656","display_name":"Entrainment (biomusicology)","level":3,"score":0.5174389481544495},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47046029567718506},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.43660491704940796},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4159262180328369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3625261187553406},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35936439037323},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.13826322555541992},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1005171537399292},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07048633694648743},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07011598348617554},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda50338.2020.9295020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W206967138","https://openalex.org/W854541894","https://openalex.org/W1600722501","https://openalex.org/W1902237438","https://openalex.org/W1921523184","https://openalex.org/W1935012542","https://openalex.org/W1995064588","https://openalex.org/W2085013480","https://openalex.org/W2101416990","https://openalex.org/W2102003408","https://openalex.org/W2133564696","https://openalex.org/W2154920538","https://openalex.org/W2327501763","https://openalex.org/W2518366886","https://openalex.org/W2519091744","https://openalex.org/W2604184139","https://openalex.org/W2794490148","https://openalex.org/W2938102059","https://openalex.org/W2949382160","https://openalex.org/W2963927338","https://openalex.org/W2963971656","https://openalex.org/W2964307104","https://openalex.org/W2964308564","https://openalex.org/W2972156721","https://openalex.org/W3018342478","https://openalex.org/W4295731579","https://openalex.org/W4298580827","https://openalex.org/W6603838645","https://openalex.org/W6608432165","https://openalex.org/W6623517193","https://openalex.org/W6675137922","https://openalex.org/W6675380101","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2081919107","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2114688254","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622"],"abstract_inverted_index":{"State-of-the-art":[0],"text-to-speech":[1],"(TTS)":[2],"systems":[3,15],"successfully":[4],"produce":[5],"speech":[6,58,99,113,142,172],"with":[7,148],"a":[8,91,105,110,132,158],"high":[9],"degree":[10],"of":[11,32,68,143],"intelligibility.":[12],"But":[13],"TTS":[14,54,137],"still":[16],"often":[17],"generate":[18],"monotonous":[19],"synthesized":[20,141],"speech,":[21],"unlike":[22],"natural":[23],"utterances.":[24],"Several":[25],"existing":[26],"studies":[27],"have":[28],"addressed":[29],"the":[30,44,66,119,124,127,140,144,149,170,175],"issue":[31],"modeling":[33],"speaking":[34,69,128,151,176],"style":[35],"variations":[36],"in":[37,60],"TTSs.":[38],"Unfortunately,":[39],"scant":[40],"research":[41],"has":[42],"discussed":[43],"dialog":[45,92,159],"and":[46,63,84,95,122,126,130],"entrainment":[47,59],"context.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,107],"address":[53],"waveform":[55],"generation":[56],"toward":[57],"human-machine":[61],"communication":[62],"focus":[64],"on":[65,97,157],"synchronization":[67],"rates":[70],"that":[71,116,138,164],"may":[72],"vary":[73],"within":[74],"an":[75],"utterance,":[76],"i.e.,":[77],"slowing":[78],"down":[79],"to":[80,87,118,168],"emphasize":[81],"specific":[82],"words":[83],"distinguish":[85],"elements":[86],"highlight.":[88],"We":[89],"assume":[90],"system":[93],"exists":[94],"concentrate":[96],"its":[98],"processing":[100],"part.":[101],"To":[102],"perform":[103],"such":[104],"task,":[106],"develop":[108],"(1)":[109],"multi-task":[111],"automatic":[112],"recognition":[114],"(ASR)":[115],"listens":[117],"conversation":[120],"partner":[121],"recognizes":[123],"content":[125],"rate":[129],"(2)":[131],"generative":[133],"adversarial":[134],"network":[135],"(GAN)-based":[136],"produces":[139],"response":[145],"while":[146],"entraining":[147],"partner's":[150],"rate.":[152,177],"The":[153],"evaluation":[154],"is":[155,166],"performed":[156],"corpus.":[160],"Our":[161],"results":[162],"reveal":[163],"it":[165],"possible":[167],"entrain":[169],"input":[171],"by":[173],"synchronizing":[174]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
