{"id":"https://openalex.org/W4403279253","doi":"https://doi.org/10.1109/is61756.2024.10705252","title":"FastSpeech2 Based Japanese Emotional Speech Synthesis","display_name":"FastSpeech2 Based Japanese Emotional Speech Synthesis","publication_year":2024,"publication_date":"2024-08-29","ids":{"openalex":"https://openalex.org/W4403279253","doi":"https://doi.org/10.1109/is61756.2024.10705252"},"language":"en","primary_location":{"id":"doi:10.1109/is61756.2024.10705252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is61756.2024.10705252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Conference on Intelligent Systems (IS)","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/A5105217367","display_name":"Masaki Ikeda","orcid":null},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masaki Ikeda","raw_affiliation_strings":["University of Aizu,Information Systems Division,Aizuwakamatsu,Japan"],"affiliations":[{"raw_affiliation_string":"University of Aizu,Information Systems Division,Aizuwakamatsu,Japan","institution_ids":["https://openalex.org/I141591182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039443541","display_name":"Konstantin Markov","orcid":"https://orcid.org/0000-0003-1838-4789"},"institutions":[{"id":"https://openalex.org/I141591182","display_name":"University of Aizu","ror":"https://ror.org/02pg0e883","country_code":"JP","type":"education","lineage":["https://openalex.org/I141591182"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Konstantin Markov","raw_affiliation_strings":["University of Aizu,Information Systems Division,Aizuwakamatsu,Japan"],"affiliations":[{"raw_affiliation_string":"University of Aizu,Information Systems Division,Aizuwakamatsu,Japan","institution_ids":["https://openalex.org/I141591182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5105217367"],"corresponding_institution_ids":["https://openalex.org/I141591182"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15475256,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8730999827384949,"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":0.8730999827384949,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.8095999956130981,"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/T12031","display_name":"Speech and dialogue systems","score":0.7706000208854675,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.658984363079071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5753089189529419},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4989035129547119},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3561301827430725}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.658984363079071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5753089189529419},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4989035129547119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3561301827430725}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/is61756.2024.10705252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/is61756.2024.10705252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 12th International Conference on Intelligent Systems (IS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2002268800","https://openalex.org/W2039800941","https://openalex.org/W2964243274","https://openalex.org/W2976159681","https://openalex.org/W3015586278","https://openalex.org/W3015826515","https://openalex.org/W3015841875","https://openalex.org/W3095545636","https://openalex.org/W3107262928","https://openalex.org/W3160329778","https://openalex.org/W3196308991","https://openalex.org/W3197034238","https://openalex.org/W4221163454","https://openalex.org/W4372340836","https://openalex.org/W4385993826","https://openalex.org/W4391020683","https://openalex.org/W4398152753","https://openalex.org/W6745289305","https://openalex.org/W6746238782","https://openalex.org/W6750489868","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6790220310","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Modeling":[0],"emotions":[1],"is":[2,13,76,81,85,128],"an":[3,30,99],"important":[4],"part":[5],"of":[6,51,58,125,161],"text-to-speech":[7],"(TTS)":[8],"research":[9],"since":[10],"its":[11],"goal":[12],"to":[14,28,86,117],"develop":[15],"a":[16,47,69,159],"technology":[17],"for":[18,34],"synthesizing":[19],"naturally":[20],"sounding":[21],"speech.":[22],"In":[23],"this":[24,79],"study,":[25],"we":[26],"aimed":[27],"build":[29],"end-to-end":[31],"TTS":[32],"system":[33],"the":[35,44,52,60,64,77,123,167],"Japanese":[36],"language":[37],"that":[38,153],"can":[39],"synthesize":[40],"emotional":[41],"speech":[42],"taking":[43],"FastSpeech2":[45],"as":[46],"base":[48,168],"model.":[49],"Most":[50],"existing":[53],"approaches":[54],"use":[55],"some":[56],"form":[57],"conditioning":[59,80,121],"generation":[61],"process":[62],"on":[63],"emotion":[65,103,120],"class":[66],"label":[67],"through":[68],"corresponding":[70],"embedding.":[71,104],"What":[72],"separates":[73],"such":[74],"methods":[75],"way":[78],"implemented.":[82],"Our":[83],"approach":[84,155],"add":[87],"two":[88],"new":[89],"blocks":[90,97],"which":[91],"are":[92,106],"essentially":[93],"transformer":[94],"multi-head":[95],"self-attention":[96],"having":[98],"input":[100],"combined":[101],"with":[102],"They":[105],"inserted":[107],"before":[108],"and":[109,114,135,142],"after":[110],"FastSpeech2's":[111],"variance":[112],"adaptor":[113],"share":[115],"parameters":[116],"ensure":[118],"robust":[119],"when":[122],"amount":[124],"training":[126],"data":[127],"small.":[129],"The":[130,149],"proposed":[131],"model":[132],"was":[133],"objectively":[134],"subjectively":[136],"evaluated":[137],"using":[138],"Mel-Cepstrum":[139],"Distortion":[140],"(MCD)":[141],"Mean":[143],"Opinion":[144],"Score":[145],"(MOS)":[146],"criteria":[147],"respectively.":[148],"obtained":[150,164],"results":[151],"show":[152],"our":[154],"performs":[156],"better":[157],"than":[158],"collection":[160],"emotion-specific":[162],"models":[163],"by":[165],"fine-tuning":[166],"FastSpeech2.":[169]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}