{"id":"https://openalex.org/W2525842011","doi":"https://doi.org/10.21437/ssw.2016-10","title":"Prosodic and Spectral iVectors for Expressive Speech Synthesis","display_name":"Prosodic and Spectral iVectors for Expressive Speech Synthesis","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2525842011","doi":"https://doi.org/10.21437/ssw.2016-10","mag":"2525842011"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/105485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079323004","display_name":"Igor Jauk","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Igor Jauk","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":["Universitat Polit\u00e8cnica de Catalunya Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Polit\u00e8cnica de Catalunya Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079323004"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.8834,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84607663,"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":"59","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7107118368148804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6689064502716064},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5781265497207642},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5485501885414124},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5434671640396118},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4461216628551483},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.43768805265426636},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.42701026797294617},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.4252641797065735},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4133289158344269},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4070037603378296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40155717730522156},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3858132064342499},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3362042307853699}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7107118368148804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689064502716064},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5781265497207642},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5485501885414124},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5434671640396118},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4461216628551483},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.43768805265426636},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.42701026797294617},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.4252641797065735},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4133289158344269},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4070037603378296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40155717730522156},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3858132064342499},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3362042307853699},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2016-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/288589","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/105485","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/288589","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/105485","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G1224945033","display_name":null,"funder_award_id":"FEDER","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G2888922458","display_name":null,"funder_award_id":"TEC2015-69266-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G3375958958","display_name":null,"funder_award_id":"TEC2015-69266-P","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G4607389008","display_name":null,"funder_award_id":"MINECO/FEDER","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G4624285335","display_name":null,"funder_award_id":"MINECO/FEDER, UE","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5826542348","display_name":null,"funder_award_id":"MINECO/FEDER","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G7420919289","display_name":null,"funder_award_id":"FEDER","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G8810727461","display_name":null,"funder_award_id":"MINECO/FEDER, UE","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1599512239","https://openalex.org/W2041823554","https://openalex.org/W2087962968","https://openalex.org/W2121415728","https://openalex.org/W2123864036","https://openalex.org/W2129703931","https://openalex.org/W2150769028","https://openalex.org/W2156146072","https://openalex.org/W2282712048","https://openalex.org/W2294232014","https://openalex.org/W2295406225","https://openalex.org/W2338806053","https://openalex.org/W2401942008","https://openalex.org/W2913399920","https://openalex.org/W2981666567","https://openalex.org/W2993383518","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W2377059580","https://openalex.org/W4200355488","https://openalex.org/W127000293","https://openalex.org/W3215892509","https://openalex.org/W2928616779","https://openalex.org/W2412592434","https://openalex.org/W2010523086","https://openalex.org/W4244602709","https://openalex.org/W594987446","https://openalex.org/W2012131063"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,13,30,105],"study":[4],"on":[5,16,52,57],"the":[6,53,84,94,98,109,117,129,139,143,155,174],"suitability":[7],"of":[8,26,83,154],"prosodic":[9,39,147,163],"andacoustic":[10],"features,":[11],"with":[12],"special":[14],"focus":[15],"i-vectors,":[17],"in":[18,104],"expressivespeech":[19],"analysis":[20,153],"and":[21,40,60,164,185],"synthesis.":[22],"For":[23],"each":[24],"utterance":[25],"two":[27],"dif-ferent":[28],"databases,":[29],"laboratory":[31,144],"recorded":[32],"emotional":[33],"acted":[34],"speech,and":[35],"an":[36],"audiobook,":[37,130],"several":[38],"acoustic":[41,165],"features":[42,148],"are":[43,48,75,88,102,125,136],"ex-tracted.":[44],"Among":[45],"them,":[46],"i-vectors":[47,124],"built":[49,96],"not":[50],"only":[51],"MFCCbase,":[54],"but":[55],"also":[56],"F0,":[58],"power":[59],"syllable":[61],"durations.":[62],"Then,":[63],"un-supervised":[64],"clustering":[65],"is":[66],"performed":[67],"using":[68,116],"different":[69,132,162],"feature":[70,178],"com-binations.":[71],"The":[72,100,169],"resulting":[73],"clusters":[74,95,157],"evaluated":[76],"calculating":[77],"clus-ter":[78],"entropy":[79],"for":[80,128,142,183],"labeled":[81],"portions":[82],"databases.":[85],"Additionally,synthetic":[86],"voices":[87,101],"trained,":[89],"applying":[90],"speaker":[91],"adaptive":[92],"training,from":[93],"from":[97],"audiobook.":[99],"eval-uated":[103],"perceptual":[106,170],"test":[107],"where":[108,131],"participants":[110],"have":[111],"to":[112,167],"edit":[113],"anaudiobook":[114],"paragraph":[115],"synthetic":[118],"voices.The":[119],"objective":[120],"results":[121,171],"suggest":[122,158,172],"that":[123,159,173],"very":[126],"use-ful":[127],"speakers":[133],"(book":[134],"charac-ters)":[135],"imitated.":[137],"On":[138],"other":[140],"hand,":[141],"record-ings,":[145],"traditional":[146],"outperform":[149],"i-vectors.":[150],"Also,a":[151],"closer":[152],"created":[156],"differentspeakers":[160],"use":[161],"means":[166],"conveyemotions.":[168],"proposed":[175],"i-vector":[176],"based":[177],"combinations":[179],"can":[180],"be":[181],"used":[182],"audiobookclustering":[184],"voice":[186],"training.":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
