{"id":"https://openalex.org/W2885800352","doi":"https://doi.org/10.1109/slt.2018.8639682","title":"Predicting Expressive Speaking Style from Text in End-To-End Speech Synthesis","display_name":"Predicting Expressive Speaking Style from Text in End-To-End Speech Synthesis","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2885800352","doi":"https://doi.org/10.1109/slt.2018.8639682","mag":"2885800352"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5024684905","display_name":"Daisy Stanton","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daisy Stanton","raw_affiliation_strings":["Google, Inc., Mountain View, CA 94043"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA 94043","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Google, Inc., Mountain View, CA 94043"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA 94043","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066591543","display_name":"RJ Skerry-Ryan","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"RJ Skerry-Ryan","raw_affiliation_strings":["Google, Inc., Mountain View, CA 94043"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA 94043","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5024684905"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":10.4917,"has_fulltext":false,"cited_by_count":116,"citation_normalized_percentile":{"value":0.98485068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"595","last_page":"602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.998199999332428,"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":0.9980000257492065,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7148032188415527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6621738076210022},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6241176724433899},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.592479407787323},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5617079138755798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4846685230731964},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4054625332355499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3631291091442108},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.09606719017028809},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.08229449391365051},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06716004014015198}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7148032188415527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6621738076210022},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6241176724433899},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.592479407787323},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5617079138755798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4846685230731964},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4054625332355499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3631291091442108},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.09606719017028809},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.08229449391365051},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06716004014015198}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W83385698","https://openalex.org/W162654330","https://openalex.org/W174066062","https://openalex.org/W1522301498","https://openalex.org/W1967177300","https://openalex.org/W2099057450","https://openalex.org/W2150769028","https://openalex.org/W2157331557","https://openalex.org/W2408520939","https://openalex.org/W2599621350","https://openalex.org/W2603120115","https://openalex.org/W2736900972","https://openalex.org/W2747227176","https://openalex.org/W2761514455","https://openalex.org/W2780113219","https://openalex.org/W2791489977","https://openalex.org/W2793479148","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2901611695","https://openalex.org/W2950635152","https://openalex.org/W2962691331","https://openalex.org/W2963196848","https://openalex.org/W2963272440","https://openalex.org/W2963609956","https://openalex.org/W2963857374","https://openalex.org/W2964121744","https://openalex.org/W4242640703","https://openalex.org/W4295731579","https://openalex.org/W4327693937","https://openalex.org/W6606697926","https://openalex.org/W6607127583","https://openalex.org/W6631190155","https://openalex.org/W6674887261","https://openalex.org/W6741475896","https://openalex.org/W6742898050","https://openalex.org/W6747279884","https://openalex.org/W6749154389","https://openalex.org/W6750489868","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W2763956190","https://openalex.org/W4404782863"],"abstract_inverted_index":{"Global":[0,44],"Style":[1,45],"Tokens":[2],"(GSTs)":[3],"are":[4],"a":[5,22,151],"recently-proposed":[6],"method":[7],"to":[8,28,66],"learn":[9],"latent":[10],"disentangled":[11],"representations":[12],"of":[13,32,161],"high-dimensional":[14],"data.":[15],"GSTs":[16],"can":[17,96,115],"be":[18],"used":[19],"within":[20,62],"Tacotron,":[21],"state-of-the-art":[23,107],"end-to-end":[24],"text-to-speech":[25],"synthesis":[26],"system,":[27],"uncover":[29],"expressive":[30,91],"factors":[31],"variation":[33,104],"in":[34],"speaking":[35,59,147],"style.":[36,148],"In":[37],"this":[38],"work,":[39],"we":[40,136],"introduce":[41],"the":[42],"Text-Predicting":[43],"Token":[46],"(TP-GST)":[47],"architecture,":[48],"which":[49],"treats":[50],"GST":[51],"combination":[52],"weights":[53],"or":[54],"style":[55,60],"embeddings":[56],"as":[57],"\u201cvirtual\u201d":[58],"labels":[61,76],"Tacotron.":[63],"TP-GST":[64,140],"learns":[65],"predict":[67],"stylistic":[68],"renderings":[69],"from":[70],"text":[71,98],"alone,":[72],"requiring":[73],"neither":[74],"explicit":[75],"during":[77],"training,":[78],"nor":[79],"auxiliary":[80],"inputs":[81],"for":[82,159],"inference.":[83],"We":[84,110,149],"show":[85],"that,":[86],"when":[87],"trained":[88],"on":[89,129],"an":[90],"speech":[92,117],"dataset,":[93],"our":[94,162],"system":[95],"render":[97],"with":[99,118,126,153],"more":[100],"pitch":[101],"and":[102,122,146],"energy":[103],"than":[105],"two":[106],"baseline":[108],"models.":[109],"further":[111],"demonstrate":[112,137],"that":[113,138],"TP-GSTs":[114],"synthesize":[116],"background":[119],"noise":[120],"removed,":[121],"corroborate":[123],"these":[124],"analyses":[125],"positive":[127],"results":[128],"human-rated":[130],"listener":[131],"preference":[132],"audiobook":[133],"tasks.":[134],"Finally,":[135],"multi-speaker":[139],"models":[141],"successfully":[142],"factorize":[143],"speaker":[144],"identity":[145],"provide":[150],"website":[152],"audio":[154],"samples":[155],"<sup":[156],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[157],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[158],"each":[160],"findings.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}