{"id":"https://openalex.org/W3198123658","doi":"https://doi.org/10.21437/interspeech.2021-465","title":"Expressive Text-to-Speech Using Style Tag","display_name":"Expressive Text-to-Speech Using Style Tag","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198123658","doi":"https://doi.org/10.21437/interspeech.2021-465","mag":"3198123658"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-465","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-465","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/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minchan Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005088101","display_name":"Sung Jun Cheon","orcid":"https://orcid.org/0000-0002-7293-6997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung Jun Cheon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424423","display_name":"Byoung Jin Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Byoung Jin Choi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066090703","display_name":"Jong Jin Kim","orcid":"https://orcid.org/0000-0001-5772-6425"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jong Jin Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027616639"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8199,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.87906712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4663","last_page":"4667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9937000274658203,"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":0.9937000274658203,"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/T12031","display_name":"Speech and dialogue systems","score":0.9757000207901001,"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":0.9648000001907349,"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":0.820275068283081},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6743079423904419},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6742277145385742},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5545194745063782},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.522331178188324},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4780219793319702},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4718354344367981},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4686022996902466},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45270204544067383},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44862961769104004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4229002594947815},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4107498228549957},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3389729857444763},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.062297970056533813}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.820275068283081},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6743079423904419},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6742277145385742},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5545194745063782},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.522331178188324},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4780219793319702},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4718354344367981},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4686022996902466},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45270204544067383},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44862961769104004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4229002594947815},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4107498228549957},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3389729857444763},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.062297970056533813},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-465","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-465","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":[{"display_name":"Quality Education","score":0.6899999976158142,"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/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W632157940","https://openalex.org/W2387981414","https://openalex.org/W1567410843"],"abstract_inverted_index":{"As":[0,99],"recent":[1],"text-to-speech":[2],"(TTS)":[3],"systems":[4],"have":[5],"been":[6],"rapidly":[7],"improved":[8],"in":[9,62,104,112,129,158],"speech":[10,40,159],"quality":[11,160],"and":[12,70,82,117,161],"generation":[13],"speed,":[14],"many":[15],"researchers":[16],"now":[17],"focus":[18],"on":[19],"a":[20,51,58,66,71,113],"more":[21,114],"challenging":[22],"issue:":[23],"expressive":[24,31,53,154],"TTS.":[25],"To":[26],"control":[27,109],"speaking":[28,83,110],"styles,":[29],"existing":[30,153],"TTS":[32,54,68,140,155],"models":[33],"use":[34],"categorical":[35],"style":[36,42,59,84,94,100,111,122],"index":[37,123],"or":[38,124],"reference":[39,125],"as":[41],"input.":[43],"In":[44,127],"this":[45],"work,":[46],"we":[47,75,134],"propose":[48,135],"StyleTagging-TTS":[49],"(ST-TTS),":[50],"novel":[52],"model":[55,89,132],"that":[56,149],"utilizes":[57],"tag":[60,101],"written":[61,103],"natural":[63,105],"language.":[64],"Using":[65],"style-tagged":[67],"dataset":[69],"pre-trained":[72],"language":[73],"model,":[74,156],"modeled":[76],"the":[77,152],"relationship":[78],"between":[79],"linguistic":[80],"embedding":[81],"domain,":[85],"which":[86],"enables":[87],"our":[88],"to":[90],"work":[91],"even":[92],"with":[93,121,142],"tags":[95],"unseen":[96],"during":[97],"training.":[98,144],"is":[102],"language,":[106],"it":[107],"can":[108],"intuitive,":[115],"interpretable,":[116],"scalable":[118],"way":[119],"compared":[120],"speech.":[126],"addition,":[128],"terms":[130],"of":[131],"architecture,":[133],"an":[136],"efficient":[137],"non-autoregressive":[138],"(NAR)":[139],"architecture":[141],"single-stage":[143],"The":[145],"experimental":[146],"result":[147],"shows":[148],"ST-TTS":[150],"outperforms":[151],"Tacotron2-GST":[157],"expressiveness.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}
