{"id":"https://openalex.org/W2785364623","doi":"https://doi.org/10.1109/apsipa.2017.8282231","title":"An investigation to transplant emotional expressions in DNN-based TTS synthesis","display_name":"An investigation to transplant emotional expressions in DNN-based TTS synthesis","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785364623","doi":"https://doi.org/10.1109/apsipa.2017.8282231","mag":"2785364623"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5082312736","display_name":"Katsuki Inoue","orcid":null},"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":["Graduate School of Natural Science and Technology, Okayama University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Natural Science and Technology, Okayama University, 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"},"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":["Graduate School of Natural Science and Technology, Okayama University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Natural Science and Technology, Okayama University, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063057571","display_name":"Masanobu Abe","orcid":"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":["Graduate School of Natural Science and Technology, Okayama University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Natural Science and Technology, Okayama University, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"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":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1253","last_page":"1258"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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":0.9918000102043152,"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/speech-recognition","display_name":"Speech recognition","score":0.7043347358703613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6996086835861206},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5988905429840088},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.576823890209198},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5356801152229309},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5168178677558899},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44292593002319336},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4307316243648529},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39963269233703613},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31727153062820435},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20817267894744873}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7043347358703613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996086835861206},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5988905429840088},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.576823890209198},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5356801152229309},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5168178677558899},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44292593002319336},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4307316243648529},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39963269233703613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31727153062820435},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20817267894744873},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1499332833","https://openalex.org/W1931958196","https://openalex.org/W2039800941","https://openalex.org/W2049686551","https://openalex.org/W2082426107","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2102003408","https://openalex.org/W2134973740","https://openalex.org/W2153914468","https://openalex.org/W2398561585","https://openalex.org/W2494654097","https://openalex.org/W2516321201","https://openalex.org/W2605320104","https://openalex.org/W2759925408","https://openalex.org/W6713020357","https://openalex.org/W6736204136"],"related_works":["https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3147584709","https://openalex.org/W3200723557","https://openalex.org/W4312713546","https://openalex.org/W2216757598","https://openalex.org/W2362195430","https://openalex.org/W2347494122","https://openalex.org/W2567983276"],"abstract_inverted_index":{"In":[0,161,186],"this":[1,188],"paper,":[2],"we":[3],"investigate":[4],"deep":[5],"neural":[6],"network":[7],"(DNN)":[8],"architectures":[9],"to":[10,14,26,58,62],"transplant":[11,63],"emotional":[12,165,205],"expressions":[13],"improve":[15],"the":[16,60,79,97,115,172,178,184,192,195,198,209],"expressiveness":[17],"of":[18,45,73,88,106,125,163,197],"DNN-based":[19],"text-to-speech":[20],"(TTS)":[21],"synthesis.":[22],"DNN":[23,46,74],"is":[24,194],"expected":[25],"have":[27,48,52],"potential":[28],"power":[29],"in":[30],"mapping":[31],"between":[32],"linguistic":[33],"information":[34],"and":[35,51,93,127,147,150,180],"acoustic":[36],"features.":[37],"From":[38],"multispeaker":[39],"and/or":[40],"multi-language":[41],"perspectives,":[42],"several":[43],"types":[44,72],"architecture":[47,75],"been":[49],"proposed":[50],"shown":[53],"good":[54],"performances.":[55],"We":[56],"tried":[57],"expand":[59],"idea":[61],"emotion,":[64],"constructing":[65],"shared":[66],"emotion-dependent":[67,94,107],"mappings.":[68],"The":[69,136],"following":[70],"three":[71,199],"are":[76],"examined;":[77],"(1)":[78],"parallel":[80],"model":[81,99,118],"(PM)":[82],"with":[83,101,120],"an":[84,102,121],"output":[85,103],"layer":[86,104,123],"consisting":[87,105,124],"both":[89],"speaker-":[90],"dependent":[91],"layers":[92,108],"layers,":[95,113],"(2)":[96],"serial":[98],"(SM)":[100],"preceded":[109],"by":[110,144,154,208],"speaker-dependent":[111],"hidden":[112],"(3)":[114],"auxiliary":[116],"input":[117,122],"(AIM)":[119],"emotion":[126],"speaker":[128],"IDs":[129],"as":[130,132],"well":[131],"linguistics":[133],"feature":[134],"vectors.":[135],"DNNs":[137],"were":[138],"trained":[139],"using":[140],"neutral":[141],"speech":[142,149,152,206],"uttered":[143,153,207],"24":[145,159],"speakers,":[146],"sad":[148],"joyful":[151],"3":[155],"speakers":[156],"from":[157],"those":[158],"speakers.":[160],"terms":[162],"unseen":[164],"synthesis,":[166],"subjective":[167],"evaluation":[168],"tests":[169],"showed":[170,190],"that":[171,191],"PM":[173],"performs":[174],"much":[175],"better":[176,182],"than":[177,183],"SM":[179,193],"slightly":[181],"AIM.":[185],"addition,":[187],"test":[189],"best":[196],"models":[200],"when":[201],"training":[202],"data":[203],"includes":[204],"target":[210],"speaker.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}