{"id":"https://openalex.org/W4382698917","doi":"https://doi.org/10.1142/s2717554523500078","title":"FastSpeechStyle: Fast, Emotion Controllable, and High-Quality Speech Synthesis","display_name":"FastSpeechStyle: Fast, Emotion Controllable, and High-Quality Speech Synthesis","publication_year":2022,"publication_date":"2022-09-01","ids":{"openalex":"https://openalex.org/W4382698917","doi":"https://doi.org/10.1142/s2717554523500078"},"language":"en","primary_location":{"id":"doi:10.1142/s2717554523500078","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s2717554523500078","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-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/A5090931215","display_name":"Van-Thinh Nguyen","orcid":"https://orcid.org/0000-0002-6240-0937"},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Van-Thinh Nguyen","raw_affiliation_strings":["VinBigData, Vingroup, Hanoi, 100000, Vietnam"],"raw_orcid":"https://orcid.org/0000-0002-6240-0937","affiliations":[{"raw_affiliation_string":"VinBigData, Vingroup, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081461430","display_name":"Tri-Nhan Do","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tri-Nhan Do","raw_affiliation_strings":["VinBigData, Vingroup, Hanoi, 100000, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VinBigData, Vingroup, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028421898","display_name":"Hung Cuong Pham","orcid":"https://orcid.org/0000-0003-4187-6335"},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hung-Cuong Pham","raw_affiliation_strings":["VinBigData, Vingroup, Hanoi, 100000, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VinBigData, Vingroup, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101219039","display_name":"Tuan-Vu Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tuan-Vu Ho","raw_affiliation_strings":["School of Information Science, Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, 923-1211, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science, Japan Advanced Institute of Science and Technology, 1-1 Asahidai, Nomi, Ishikawa, 923-1211, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098246283","display_name":"Minh-Khanh Nguyen Ngoc","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Khanh Nguyen Ngoc","raw_affiliation_strings":["VinBigData, Vingroup, Hanoi, 100000, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VinBigData, Vingroup, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041474728","display_name":"\u0110\u0103ng-Khoa M\u1ea1c","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142044","display_name":"VinUniversity","ror":"https://ror.org/052dmdr17","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210142044"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Dang-Khoa Mac","raw_affiliation_strings":["VinBigData, Vingroup, Hanoi, 100000, Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VinBigData, Vingroup, Hanoi, 100000, Vietnam","institution_ids":["https://openalex.org/I4210142044"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19668489,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"02n03","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.993399977684021,"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/T10860","display_name":"Speech and Audio Processing","score":0.9891999959945679,"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/naturalness","display_name":"Naturalness","score":0.8670790195465088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6773431301116943},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.673303484916687},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5910943150520325},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5722690224647522},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5657669305801392},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5485747456550598},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5094423890113831},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4315219521522522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36829763650894165},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2262422740459442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15166768431663513}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8670790195465088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6773431301116943},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.673303484916687},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5910943150520325},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5722690224647522},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5657669305801392},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5485747456550598},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5094423890113831},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4315219521522522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36829763650894165},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2262422740459442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15166768431663513},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s2717554523500078","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1142/s2717554523500078","pdf_url":null,"source":{"id":"https://openalex.org/S4210231678","display_name":"International Journal of Asian Language Processing","issn_l":"2424-791X","issn":["2424-791X","2717-5545"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Asian Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W141706186","https://openalex.org/W1537908555","https://openalex.org/W2084609288","https://openalex.org/W2133665775","https://openalex.org/W2169166781","https://openalex.org/W2471520273","https://openalex.org/W2904459034","https://openalex.org/W2976532777","https://openalex.org/W3016137096","https://openalex.org/W3036975059","https://openalex.org/W3150572638","https://openalex.org/W4297841375"],"related_works":["https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2433276473","https://openalex.org/W2077992636","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W290673751","https://openalex.org/W2017702615","https://openalex.org/W2024201202"],"abstract_inverted_index":{"Non-autoregressive":[0],"text-to-speech":[1],"models":[2],"such":[3],"as":[4],"Fastspeech2":[5],"can":[6,48],"fast":[7,203],"synthesize":[8,49],"high-quality":[9,50],"speech.":[10,170],"This":[11],"model":[12,46,57,147,179,189,200],"also":[13,158],"allows":[14],"explicit":[15],"control":[16,165],"of":[17,72,112,169],"the":[18,70,75,148,154,166,187,207],"speech":[19,32,44,51],"signal\u2019s":[20],"pitch,":[21],"energy,":[22],"and":[23,103,127,133,150,193],"speed.":[24],"However,":[25],"controlling":[26],"emotion":[27,67,109,168,194],"while":[28],"maintaining":[29],"natural":[30],"human-like":[31],"is":[33,81],"still":[34,201],"a":[35,77,160],"problem.":[36],"In":[37],"this":[38],"work,":[39],"we":[40],"propose":[41,159],"an":[42,89],"expressive":[43],"synthesis":[45],"that":[47,175],"with":[52,97,180],"desired":[53,167],"emotion.":[54],"The":[55,86,171,177,198],"proposed":[56,178,199],"includes":[58],"two":[59],"main":[60],"components":[61],"(1)":[62,176],"Mel":[63],"Emotion":[64],"Encoder":[65],"extracts":[66],"embedding":[68],"from":[69,83],"Mel-spectrogram":[71],"audio,":[73],"(2)":[74,197],"FastSpeechStyle,":[76],"non-autoregressive":[78],"model,":[79],"which":[80,93],"modified":[82],"vanilla":[84,113],"Fastspeech2.":[85],"FastSpeechStyle":[87],"used":[88],"Improved":[90],"Conformer":[91,182],"block,":[92],"replaces":[94],"normal":[95],"LayerNorm":[96,100],"Style":[98],"Adaptive":[99],"to":[101,108,136,145,164],"\u201cshift\u201d":[102],"\u201cscale\u201d":[104],"hidden":[105],"features":[106],"according":[107],"embedding,":[110],"instead":[111],"FFTBlock":[114],"[Y.":[115],"Ren,":[116],"Y.":[117],"Ruan,":[118],"X.":[119],"Tan,":[120],"T.":[121],"Qin,":[122],"S.":[123],"Zhao,":[124],"Z.":[125],"Zhao":[126],"T.-Y.":[128],"Liu,":[129],"Fastspeech:":[130],"Fast,":[131],"robust":[132],"controllable":[134],"text":[135],"speech,":[137],"Adv.":[138],"Neural":[139],"Inf.":[140],"Process.":[141],"Syst.":[142],"32":[143],"(2019)]":[144],"better":[146],"local":[149],"global":[151],"dependency":[152],"in":[153,190],"acoustic":[155],"model.":[156,209],"We":[157],"specific":[161],"inference":[162,204],"strategy":[163],"experimental":[172],"results":[173],"show":[174],"improved":[181],"achieved":[183],"higher":[184],"scores":[185],"than":[186],"baseline":[188,208],"all":[191],"naturalness":[192],"similarity":[195],"scores;":[196],"maintains":[202],"speed":[205],"like":[206]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}