{"id":"https://openalex.org/W3159045181","doi":"https://doi.org/10.21437/interspeech.2021-1538","title":"Exploring Emotional Prototypes in a High Dimensional TTS Latent Space","display_name":"Exploring Emotional Prototypes in a High Dimensional TTS Latent Space","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3159045181","doi":"https://doi.org/10.21437/interspeech.2021-1538","mag":"3159045181"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1538","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1538","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.01891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045500067","display_name":"Pol van Rijn","orcid":"https://orcid.org/0000-0002-4044-9123"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pol van Rijn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043580137","display_name":"Silvan Mertes","orcid":"https://orcid.org/0000-0001-5230-5218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silvan Mertes","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060629499","display_name":"Dominik Schiller","orcid":"https://orcid.org/0000-0001-7364-5772"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dominik Schiller","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032482902","display_name":"Peter M. C. Harrison","orcid":"https://orcid.org/0000-0002-9851-9462"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter M.C. Harrison","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055706999","display_name":"Pauline Larrouy-Maestri","orcid":"https://orcid.org/0000-0001-9245-0743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pauline Larrouy-Maestri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056684559","display_name":"Elisabeth Andr\u00e9","orcid":"https://orcid.org/0000-0002-2367-162X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elisabeth Andr\u00e9","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021757437","display_name":"Nori Jacoby","orcid":"https://orcid.org/0000-0003-2868-0100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nori Jacoby","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5045500067"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.5046,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.98647632,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3870","last_page":"3874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.991100013256073,"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":0.9869999885559082,"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/prosody","display_name":"Prosody","score":0.6383184194564819},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6111170053482056},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5642424821853638},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5590662360191345},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5345838069915771},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.5231051445007324},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.5196829438209534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4966941475868225},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.47772857546806335},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.442929208278656},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3973504602909088},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3582714796066284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3180692493915558}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6383184194564819},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6111170053482056},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5642424821853638},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5590662360191345},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5345838069915771},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.5231051445007324},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.5196829438209534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4966941475868225},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.47772857546806335},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.442929208278656},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3973504602909088},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3582714796066284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3180692493915558},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1538","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1538","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"},{"id":"pmh:oai:arXiv.org:2105.01891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.01891","pdf_url":"https://arxiv.org/pdf/2105.01891","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:89689","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-896892","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/331558","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/331558","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"},{"id":"doi:10.17863/cam.79011","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.79011","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.01891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.01891","pdf_url":"https://arxiv.org/pdf/2105.01891","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5099999904632568,"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":18,"referenced_works":["https://openalex.org/W2085876742","https://openalex.org/W2090777335","https://openalex.org/W2105889829","https://openalex.org/W2148031978","https://openalex.org/W2239141610","https://openalex.org/W2560925688","https://openalex.org/W2735131873","https://openalex.org/W2884225676","https://openalex.org/W2912483755","https://openalex.org/W2963272440","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964243274","https://openalex.org/W3015645837","https://openalex.org/W3025528898","https://openalex.org/W3105925062","https://openalex.org/W3209383001","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W2280377497","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Recent":[0],"TTS":[1],"systems":[2],"are":[3,58,107,118],"able":[4],"to":[5,21,39,51,82,136,146,156],"generate":[6],"prosodically":[7],"varied":[8],"and":[9,61,127,167],"realistic":[10],"speech.":[11],"However,":[12],"it":[13],"is":[14,87],"unclear":[15],"how":[16],"this":[17],"prosodic":[18,42],"variation":[19],"contributes":[20],"the":[22,31,41,64,68,79,90,93,103,114,147,158,161],"perception":[23],"of":[24,54,67,85,92,102,124,149,164],"speakers'":[25],"emotional":[26,55,116,130,150],"states.":[27],"Here":[28],"we":[29],"use":[30],"recent":[32],"psychological":[33],"paradigm":[34],"'Gibbs":[35],"Sampling":[36],"with":[37,110],"People'":[38],"search":[40],"latent":[43,65,105,162],"space":[44,66,106,163],"in":[45,72],"a":[46,73,121,143,154],"trained":[47],"GST":[48],"Tacotron":[49],"model":[50,71],"explore":[52,157],"prototypes":[53,117,131],"prosody.":[56],"Participants":[57],"recruited":[59],"online":[60],"collectively":[62],"manipulate":[63],"generative":[69,165],"speech":[70,151],"sequentially":[74],"adaptive":[75],"way":[76],"so":[77],"that":[78,98],"stimulus":[80],"presented":[81],"one":[83],"group":[84,123],"participants":[86],"determined":[88],"by":[89,120,152],"response":[91],"previous":[94],"groups.":[95],"We":[96],"demonstrate":[97,142],"(1)":[99],"particular":[100,111],"regions":[101],"model's":[104],"reliably":[108],"associated":[109],"emotions,":[112],"(2)":[113],"resulting":[115],"well-recognized":[119],"separate":[122],"human":[125,168],"raters,":[126],"(3)":[128],"these":[129,140],"can":[132],"be":[133],"effectively":[134],"transferred":[135],"new":[137],"sentences.":[138],"Collectively,":[139],"experiments":[141],"novel":[144],"approach":[145],"understanding":[148],"providing":[153],"tool":[155],"relation":[159],"between":[160],"models":[166],"semantics.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
