{"id":"https://openalex.org/W3132489765","doi":null,"title":"Module Comparison Of Transformer-Tts For Speaker Adaptation Based On Fine-Tuning","display_name":"Module Comparison Of Transformer-Tts For Speaker Adaptation Based On Fine-Tuning","publication_year":2020,"publication_date":"2020-12-07","ids":{"openalex":"https://openalex.org/W3132489765","mag":"3132489765"},"language":"en","primary_location":{"id":"mag:3132489765","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/apsipa/apsipa2020.html#InoueHA20","pdf_url":null,"source":{"id":"https://openalex.org/S4363607812","display_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5082312736","display_name":"Katsuki Inoue","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuki Inoue","raw_affiliation_strings":["Okayama University,The Graduate School of Interdisciplinary Science and Engineering in Health Systems,Okayama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Okayama University,The Graduate School of Interdisciplinary Science and Engineering in Health Systems,Okayama,Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070197974","display_name":"Sunao Hara","orcid":"https://orcid.org/0000-0001-5972-5178","observed_orcids":["https://orcid.org/0000-0001-5972-5178"]},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sunao Hara","raw_affiliation_strings":["Okayama University,The Graduate School of Interdisciplinary Science and Engineering in Health Systems,Okayama,Japan"],"raw_orcid":"https://orcid.org/0000-0001-5972-5178","affiliations":[{"raw_affiliation_string":"Okayama University,The Graduate School of Interdisciplinary Science and Engineering in Health Systems,Okayama,Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063057571","display_name":"Masanobu Abe","orcid":"https://orcid.org/0000-0001-9472-5077","observed_orcids":["https://orcid.org/0000-0001-9472-5077"]},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanobu Abe","raw_affiliation_strings":["Okayama University,The Graduate School of Interdisciplinary Science and Engineering in Health Systems,Okayama,Japan"],"raw_orcid":"https://orcid.org/0000-0001-9472-5077","affiliations":[{"raw_affiliation_string":"Okayama University,The Graduate School of Interdisciplinary Science and Engineering in Health Systems,Okayama,Japan","institution_ids":["https://openalex.org/I163770644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I163770644"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"826","last_page":"830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.0,"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/T10863","display_name":"Voice and Speech Disorders","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-adaptation","display_name":"speaker adaptation","score":0.718999981880188},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8600000143051147},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.9190000295639038},{"id":"https://openalex.org/keywords/character-level-embeddings","display_name":"character embeddings","score":0.7049999833106995},{"id":"https://openalex.org/keywords/encoder","display_name":"encoder","score":0.6589999794960022},{"id":"https://openalex.org/keywords/speech-repetition","display_name":"speech repetition","score":0.9300000071525574},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.8259999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520369291305542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7341887950897217},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7302778363227844},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.684607982635498},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5660876035690308},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49917125701904297},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4840206801891327},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4576922357082367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2702106833457947},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1307210922241211},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08861306309700012},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3132489765","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/apsipa/apsipa2020.html#InoueHA20","pdf_url":null,"source":{"id":"https://openalex.org/S4363607812","display_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2100495367","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2120480077","https://openalex.org/W2165698076","https://openalex.org/W2626778328","https://openalex.org/W2766812927","https://openalex.org/W2890964092","https://openalex.org/W2903739847","https://openalex.org/W2909192763","https://openalex.org/W2913340405","https://openalex.org/W2953337107","https://openalex.org/W2962780374","https://openalex.org/W2963192573","https://openalex.org/W2963432880","https://openalex.org/W2963796886","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2972359262","https://openalex.org/W2972818416","https://openalex.org/W2972970915","https://openalex.org/W2973034126","https://openalex.org/W3015338123","https://openalex.org/W3015853838","https://openalex.org/W3016160783"],"related_works":["https://openalex.org/W4385822455","https://openalex.org/W4392905338","https://openalex.org/W7214146246","https://openalex.org/W4307783813","https://openalex.org/W4405270664","https://openalex.org/W4402112213","https://openalex.org/W3015853838","https://openalex.org/W3205133942","https://openalex.org/W4406840843","https://openalex.org/W3214343901"],"abstract_inverted_index":{"End-to-end":[0],"text-to-speech":[1],"(TTS)":[2],"models":[3],"have":[4],"achieved":[5],"remarkable":[6],"results":[7,136],"in":[8,109,148,151],"recent":[9],"times.":[10],"However,":[11],"the":[12,49,58,72,77,83,87,92,104,110,138,142,152,163,174,193],"model":[13,39],"requires":[14],"a":[15,37],"large":[16],"amount":[17,93],"of":[18,62,66,94,106,156],"text":[19],"and":[20,127,182],"audio":[21],"data":[22,95],"for":[23,35,130],"training.":[24],"A":[25],"speaker":[26,51,67,79],"adaptation":[27,68],"method":[28],"based":[29],"on":[30,82],"fine-tuning":[31,141],"has":[32],"been":[33],"proposed":[34],"constructing":[36],"TTS":[38],"using":[40],"small":[41],"scale":[42],"data.":[43],"Although":[44],"these":[45],"methods":[46],"can":[47],"replicate":[48],"target":[50,78],"s":[52,81],"voice":[53,73],"quality,":[54],"synthesized":[55],"speech":[56,159,169,187],"includes":[57],"deletion":[59,153,160,170],"and/or":[60,154],"repetition":[61,155],"speech.":[63],"The":[64,134],"goal":[65],"is":[69,165,179,199],"to":[70,75,96],"change":[71],"quality":[74],"match":[76],"\u2019":[80],"premise":[84],"that":[85],"adjusting":[86],"necessary":[88],"modules":[89],"will":[90],"reduce":[91],"be":[97],"fine-tuned.":[98],"In":[99],"this":[100],"paper,":[101],"we":[102,118],"clarify":[103],"role":[105],"each":[107],"module":[108],"Transformer-TTS":[111],"process":[112],"by":[113],"not":[114,146,166,180],"updating":[115],"it.":[116],"Specifically,":[117],"froze":[119],"character":[120,143],"embedding,":[121],"encoder,":[122],"layer":[123,175],"predicting":[124,176],"stop":[125,177],"token,":[126],"loss":[128,194],"function":[129,195],"estimating":[131,196],"sentence":[132,190,197],"ending.":[133],"experimental":[135],"showed":[137],"following:":[139],"(1)":[140],"embedding":[144],"did":[145],"result":[147],"an":[149],"improvement":[150],"speech,":[157],"(2)":[158],"increases":[161],"if":[162],"encoder":[164],"fine-tuned,":[167,181],"(3)":[168],"was":[171],"suppressed":[172],"when":[173,192],"token":[178],"(4)":[183],"there":[184],"are":[185],"frequent":[186],"repetitions":[188],"at":[189],"end":[191],"ending":[198],"omitted.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-03-01T00:00:00"}