{"id":"https://openalex.org/W3198104520","doi":"https://doi.org/10.21437/interspeech.2021-838","title":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech","display_name":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198104520","doi":"https://doi.org/10.21437/interspeech.2021-838","mag":"3198104520"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-838","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5038620960","display_name":"Keon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Keon Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027597779","display_name":"Kyumin Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyumin Park","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100412727","display_name":"Daeyoung Kim","orcid":"https://orcid.org/0000-0001-9056-0017"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daeyoung Kim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038620960"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.253,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9010113,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4643","last_page":"4647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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/T10028","display_name":"Topic Modeling","score":0.984499990940094,"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":0.9771999716758728,"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/robustness","display_name":"Robustness (evolution)","score":0.7745660543441772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7022764682769775},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6690586805343628},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4198974370956421}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7745660543441772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7022764682769775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690586805343628},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4198974370956421},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-838","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"Previous":[0],"works":[1],"on":[2,9,79],"neural":[3],"text-to-speech":[4],"(TTS)":[5],"have":[6],"been":[7,33],"addressed":[8],"limited":[10],"speed":[11,135],"in":[12,92,134],"training":[13,73,111],"and":[14,23,50,56,67,74,76,112,136,144,147,156,165],"inference":[15,75],"time,":[16],"robustness":[17,137],"for":[18],"difficult":[19],"synthesis":[20,78],"conditions,":[21],"expressiveness,":[22],"controllability.":[24],"Although":[25],"several":[26],"approaches":[27],"resolve":[28],"some":[29],"limitations,":[30],"there":[31],"has":[32],"no":[34],"attempt":[35],"to":[36,96],"solve":[37],"all":[38],"weaknesses":[39],"at":[40],"once.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45],"propose":[46],"STYLER,":[47],"an":[48],"expressive":[49,97,139,146],"controllable":[51,148],"TTS":[52,140],"framework":[53],"with":[54,141],"high-speed":[55],"robust":[57,77],"synthesis.":[58],"Our":[59],"novel":[60,104],"audio-text":[61],"aligning":[62],"method":[63],"called":[64],"Mel":[65],"Calibrator":[66],"excluding":[68],"autoregressive":[69,142],"decoding":[70,143],"enable":[71],"rapid":[72],"unseen":[80],"data.":[81],"Also,":[82],"disentangled":[83],"style":[84,117,151],"factor":[85],"modeling":[86,106],"under":[87],"supervision":[88],"enlarges":[89],"the":[90,120],"controllability":[91],"synthesizing":[93],"process":[94],"leading":[95],"TTS.":[98,153],"On":[99],"top":[100],"of":[101],"it,":[102],"a":[103],"noise":[105,121],"pipeline":[107],"using":[108],"domain":[109],"adversarial":[110],"Residual":[113],"Decoding":[114],"empowers":[115],"noise-robust":[116],"transfer,":[118],"decomposing":[119],"without":[122],"any":[123],"additional":[124],"label.":[125],"Various":[126],"experiments":[127],"demonstrate":[128],"that":[129],"STYLER":[130],"is":[131,167],"more":[132,145],"effective":[133],"than":[138,149],"reading":[150],"non-autoregressive":[152],"Synthesis":[154],"samples":[155],"experiment":[157],"results":[158],"are":[159],"provided":[160],"via":[161],"our":[162],"demo":[163],"page,":[164],"code":[166],"available":[168],"publicly.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}