{"id":"https://openalex.org/W4375868902","doi":"https://doi.org/10.1109/icassp49357.2023.10095513","title":"Enhancement of Text-Predicting Style Token With Generative Adversarial Network for Expressive Speech Synthesis","display_name":"Enhancement of Text-Predicting Style Token With Generative Adversarial Network for Expressive Speech Synthesis","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868902","doi":"https://doi.org/10.1109/icassp49357.2023.10095513"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076754533","display_name":"Hiroki Kanagawa","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":"Hiroki Kanagawa","raw_affiliation_strings":["NTT Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","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 Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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":0.9998999834060669,"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":0.9976000189781189,"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":0.9954000115394592,"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/security-token","display_name":"Security token","score":0.7878562808036804},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7636206150054932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7535791397094727},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6786410808563232},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.56303471326828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5003764629364014},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4820626378059387},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.47939062118530273},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46980318427085876},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10581052303314209}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7878562808036804},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7636206150054932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7535791397094727},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6786410808563232},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.56303471326828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5003764629364014},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4820626378059387},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.47939062118530273},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46980318427085876},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10581052303314209},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":42,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2519091744","https://openalex.org/W2785364623","https://openalex.org/W2794490148","https://openalex.org/W2796339975","https://openalex.org/W2885800352","https://openalex.org/W2892806280","https://openalex.org/W2896457183","https://openalex.org/W2963609956","https://openalex.org/W2963684088","https://openalex.org/W2963691546","https://openalex.org/W2963971656","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W3013020904","https://openalex.org/W3015338123","https://openalex.org/W3015826515","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3151450932","https://openalex.org/W3152136404","https://openalex.org/W3158374895","https://openalex.org/W3168527213","https://openalex.org/W3216941316","https://openalex.org/W4210777104","https://openalex.org/W4221159457","https://openalex.org/W4296068758","https://openalex.org/W4297841867","https://openalex.org/W4298580827","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6685352114","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6749489859","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6795807602"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4310988119","https://openalex.org/W4285226279","https://openalex.org/W4288019534"],"abstract_inverted_index":{"This":[0,84],"work":[1],"proposes":[2],"an":[3],"advanced":[4],"text-predicting":[5],"style":[6,14,18,38,47,82,88,95,125,133,158,166],"embedding":[7,19,62],"for":[8,168],"expressive":[9],"speech":[10,25,55],"synthesis.":[11],"Text-predicting":[12],"global":[13],"token":[15],"(TPGST)":[16],"predicts":[17],"from":[20,53],"text":[21,106],"instead":[22],"of":[23,131,148],"reference":[24,41,54],"and":[26,56,144,170],"uses":[27,74],"it":[28],"to":[29,64,93,122],"condition":[30],"a":[31],"text-to-speech":[32],"synthesis":[33],"(TTS)":[34],"model,":[35],"resulting":[36],"in":[37,80,109,120,127,163],"TTS":[39,99,105,167],"without":[40],"speech.":[42],"Although":[43],"this":[44,69],"minimizes":[45],"the":[46,71,75,138,146],"embedding\u2019s":[48],"L1-loss":[49],"between":[50],"that":[51,57,136],"extracted":[52],"predicted":[58,61],"during":[59,98],"training,":[60],"tends":[63],"be":[65],"over-smoothed.":[66],"To":[67],"overcome":[68],"issue,":[70],"proposed":[72,139],"method":[73,140],"generative":[76],"adversarial":[77],"network":[78],"(GAN)":[79],"training":[81],"predictors.":[83],"not":[85],"only":[86],"improves":[87],"reproduction,":[89],"but":[90],"also":[91,103,161],"aims":[92],"reduce":[94],"conditioning":[96],"mismatch":[97],"model":[100],"training.":[101],"We":[102],"utilize":[104],"embeddings":[107],"as":[108,113,115],"other":[110],"related":[111],"work,":[112],"well":[114],"word":[116],"information":[117],"via":[118],"BERT":[119,152],"order":[121],"find":[123],"better":[124,155],"distributions":[126],"GAN.":[128],"An":[129],"evaluation":[130],"subjective":[132],"reproduction":[134],"demonstrates":[135],"1)":[137],"outperforms":[141],"conventional":[142],"TPGST,":[143],"2)":[145],"use":[147],"words":[149],"yielded":[150],"by":[151],"provides":[153],"even":[154],"performance.":[156],"Our":[157],"predictor":[159],"is":[160],"effective":[162],"attaining":[164],"unseen":[165],"\"seen\"":[169],"\"unseen\"":[171],"speakers.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}