{"id":"https://openalex.org/W3195680981","doi":"https://doi.org/10.21437/ssw.2021-19","title":"Perception of smiling voice in spontaneous speech synthesis","display_name":"Perception of smiling voice in spontaneous speech synthesis","publication_year":2021,"publication_date":"2021-08-24","ids":{"openalex":"https://openalex.org/W3195680981","doi":"https://doi.org/10.21437/ssw.2021-19","mag":"3195680981"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2021-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-329143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075857326","display_name":"Ambika Kirkland","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Ambika Kirkland","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046585387","display_name":"Marcin W\u0142odarczak","orcid":"https://orcid.org/0000-0003-3824-2980"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Marcin W\u0142odarczak","raw_affiliation_strings":["Department of Linguistics, Stockholm University, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Linguistics, Stockholm University, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015417808","display_name":"Joakim Gustafson","orcid":"https://orcid.org/0000-0002-0397-6442"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joakim Gustafson","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Eva Szekely","raw_affiliation_strings":["Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Division of Speech, Music and Hearing, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5075857326"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6305821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9445000290870667,"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":0.9445000290870667,"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/speech-recognition","display_name":"Speech recognition","score":0.6881324648857117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6398307681083679},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6322976350784302},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.547655463218689},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4234510362148285},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3029031455516815}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6881324648857117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6398307681083679},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6322976350784302},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.547655463218689},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4234510362148285},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3029031455516815},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2021-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2021-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"11th ISCA Speech Synthesis Workshop (SSW 11)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-329143","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-329143","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-329143","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-329143","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320322659","display_name":"Riksbankens Jubileumsfond","ror":"https://ror.org/02jkbm893"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1916142944","https://openalex.org/W1979278974","https://openalex.org/W2015425850","https://openalex.org/W2054305348","https://openalex.org/W2136341744","https://openalex.org/W2149342478","https://openalex.org/W2165034386","https://openalex.org/W2169113179","https://openalex.org/W2179038008","https://openalex.org/W2183686421","https://openalex.org/W2202036599","https://openalex.org/W2225419387","https://openalex.org/W2401594287","https://openalex.org/W2794490148","https://openalex.org/W2795023788","https://openalex.org/W2901285216","https://openalex.org/W2904459034","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2972606665","https://openalex.org/W2973177710","https://openalex.org/W2988937804","https://openalex.org/W2992944139","https://openalex.org/W3015645837","https://openalex.org/W3016151952","https://openalex.org/W3096392139","https://openalex.org/W3097892637"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2931662336","https://openalex.org/W2077865380","https://openalex.org/W2134894512","https://openalex.org/W2053487507","https://openalex.org/W2765597752","https://openalex.org/W2083375246","https://openalex.org/W1997436241","https://openalex.org/W127416991","https://openalex.org/W3152454717"],"abstract_inverted_index":{"Smiling":[0],"during":[1],"speech":[2,59,114,152],"production":[3],"has":[4],"been":[5],"shown":[6],"to":[7,14,48,87,149],"result":[8],"in":[9,30,72,141],"perceptible":[10],"acoustic":[11],"differences":[12],"compared":[13,71],"non-smiling":[15],"speech.":[16,33,56],"However,":[17],"there":[18],"is":[19],"a":[20,39,73,118,137],"scarcity":[21],"of":[22,27,54,58,84,127,157],"research":[23],"on":[24,45],"the":[25,52,63,82,85,92,112,125,154],"perception":[26],"\u201csmiling":[28],"voice\u201d":[29],"synthesized":[31],"spontaneous":[32,55],"In":[34],"this":[35],"study,":[36],"we":[37],"used":[38,148],"sequence-to-sequence":[40],"neural":[41],"text-tospeech":[42],"system":[43],"built":[44],"conversational":[46],"data":[47],"produce":[49],"utterances":[50,65,93],"with":[51,153],"characteristics":[53,156],"Segments":[57],"following":[60],"laughter,":[61,69,136],"and":[62],"same":[64],"not":[66],"preceded":[67,94],"by":[68,95],"were":[70,102],"perceptual":[74,155],"experiment":[75],"after":[76],"removing":[77],"laughter":[78,96],"and/or":[79],"breaths":[80],"from":[81],"beginning":[83],"utterance":[86],"determine":[88],"whether":[89],"participants":[90,110],"perceive":[91],"as":[97,99,115],"sounding":[98],"if":[100],"they":[101],"produced":[103],"while":[104],"smiling.":[105,158],"The":[106],"results":[107,133],"showed":[108],"that":[109,135],"identified":[111],"post-laughter":[113],"smiling":[116],"at":[117],"rate":[119],"significantly":[120],"greater":[121],"than":[122],"chance.":[123],"Furthermore,":[124],"effect":[126],"content":[128],"(positive/neutral/negative)":[129],"was":[130],"investigated.":[131],"These":[132],"show":[134],"spontaneous,":[138],"non-elicited":[139],"phenomenon":[140],"our":[142],"model\u2019s":[143],"training":[144],"data,":[145],"can":[146],"be":[147],"synthesize":[150],"expressive":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}