{"id":"https://openalex.org/W4406861371","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848787","title":"StylebookTTS: Zero-Shot Text-to-Speech Leveraging Unsupervised Style Representation","display_name":"StylebookTTS: Zero-Shot Text-to-Speech Leveraging Unsupervised Style Representation","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406861371","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10848787"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10848787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5102632168","display_name":"Juhwan Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhwan Yoon","raw_affiliation_strings":["Yonsei University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075112605","display_name":"Hyungseob Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungseob Lim","raw_affiliation_strings":["Yonsei University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hyeonjin Cha","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonjin Cha","raw_affiliation_strings":["Yonsei University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113564759","display_name":"Hong-Goo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["Yonsei University,Seoul,South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University,Seoul,South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23113885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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":0.9807999730110168,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9753000140190125,"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":0.7233045101165771},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.702296793460846},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6327102184295654},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6242863535881042},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6150838136672974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5508008599281311},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48661598563194275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4762820601463318},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1419219672679901}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7233045101165771},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.702296793460846},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6327102184295654},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6242863535881042},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6150838136672974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5508008599281311},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48661598563194275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4762820601463318},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1419219672679901},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/apsipaasc63619.2025.10848787","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10848787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":25,"referenced_works":["https://openalex.org/W2747874407","https://openalex.org/W2903739847","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3196584150","https://openalex.org/W3197659778","https://openalex.org/W3209059054","https://openalex.org/W3210530853","https://openalex.org/W4297841574","https://openalex.org/W4385822372","https://openalex.org/W4393147067","https://openalex.org/W6739901393","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795807602","https://openalex.org/W6796464841","https://openalex.org/W6802527329","https://openalex.org/W6805710207","https://openalex.org/W6848735303","https://openalex.org/W6851724922","https://openalex.org/W6856253845"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Zero-shot":[0],"text-to-speech":[1],"(ZS-TTS)":[2],"is":[3,99,129,157,181],"a":[4,31,60,90,102,107,135,178],"TTS":[5],"system":[6],"capable":[7],"of":[8,104,147],"generating":[9],"speech":[10,28],"in":[11,42,101,112],"voices":[12,48],"it":[13],"has":[14],"not":[15,51],"been":[16],"explicitly":[17],"trained":[18],"on.":[19],"While":[20],"many":[21],"recent":[22],"ZS-TTS":[23,62],"models":[24],"effectively":[25],"capture":[26],"target":[27,69,83,155,191],"styles":[29,111],"using":[30,134],"single":[32],"global":[33],"style":[34,70,80,97,156,192],"feature":[35],"per":[36],"speaker,":[37],"they":[38],"still":[39],"face":[40],"challenges":[41],"achieving":[43],"high":[44],"speaker":[45,123,208],"similarity":[46,209],"for":[47,119],"that":[49,64,151,165,204],"were":[50],"previously":[52],"encountered.":[53],"In":[54],"this":[55],"study,":[56],"we":[57],"propose":[58],"StylebookTTS,":[59],"novel":[61],"framework":[63],"extracts":[65],"and":[66],"utilizes":[67],"multiple":[68],"embeddings":[71,105,161],"based":[72],"on":[73],"the":[74,117,126,141,144,163,170,175,185,189,194,199],"content.":[75],"We":[76],"begin":[77],"by":[78,159,187],"extracting":[79],"information":[81,98],"from":[82,162,174,198],"speeches,":[84],"leveraging":[85],"linguistic":[86],"content":[87,132,171,195],"obtained":[88],"through":[89],"self-supervised":[91],"learning":[92],"(SSL)":[93],"model.":[94],"The":[95,153],"extracted":[96],"stored":[100],"collection":[103],"called":[106],"stylebook,":[108],"which":[109,139],"represents":[110],"an":[113,148],"unsupervised":[114],"manner":[115],"without":[116],"need":[118],"text":[120,128,142],"transcriptions":[121],"or":[122],"labeling.":[124],"Simultaneously,":[125],"input":[127],"transformed":[130],"into":[131],"features":[133,172,196],"transformer-based":[136],"text-to-unit":[137],"module,":[138],"links":[140],"to":[143,183,211],"SSL":[145],"representations":[146],"utterance":[149],"reading":[150],"text.":[152,176,200],"final":[154,190],"created":[158],"selecting":[160],"stylebook":[164],"most":[166],"closely":[167],"align":[168],"with":[169,193],"generated":[173,197],"Finally,":[177],"diffusion-based":[179],"decoder":[180],"employed":[182],"synthesize":[184],"mel-spectrogram":[186],"combining":[188],"Experimental":[201],"results":[202],"demonstrate":[203],"StylebookTTS":[205],"achieves":[206],"greater":[207],"compared":[210],"baseline":[212],"models,":[213],"while":[214],"also":[215],"being":[216],"highly":[217],"data-efficient,":[218],"requiring":[219],"significantly":[220],"less":[221],"paired":[222],"text-audio":[223],"data.":[224]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}