{"id":"https://openalex.org/W2282712048","doi":"https://doi.org/10.21437/interspeech.2015-144","title":"Creating expressive synthetic voices by unsupervised clustering of audiobooks","display_name":"Creating expressive synthetic voices by unsupervised clustering of audiobooks","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2282712048","doi":"https://doi.org/10.21437/interspeech.2015-144","mag":"2282712048"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-144","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/81613","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079323004","display_name":"Igor Jauk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Igor Jauk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006935883","display_name":"Paula Lopez\u2010Otero","orcid":"https://orcid.org/0000-0003-2859-099X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paula Lopez-Otero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051040364","display_name":"Laura Doc\u00edo-Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3838-2406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Docio-Fernandez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3380","last_page":"3384"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9940000176429749,"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/perplexity","display_name":"Perplexity","score":0.9107335209846497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7946771383285522},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7136865258216858},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5668687224388123},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560836911201477},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4738600552082062},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.42621150612831116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36598166823387146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33471134305000305},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.06745460629463196}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9107335209846497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946771383285522},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7136865258216858},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5668687224388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560836911201477},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4738600552082062},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.42621150612831116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36598166823387146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33471134305000305},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.06745460629463196},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-144","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:recercat.cat:2072/339592","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/81613","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/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/339592","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/81613","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/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W168929619","https://openalex.org/W176245312","https://openalex.org/W1599512239","https://openalex.org/W1995875735","https://openalex.org/W2059721297","https://openalex.org/W2085013480","https://openalex.org/W2087962968","https://openalex.org/W2121415728","https://openalex.org/W2129703931","https://openalex.org/W2156146072","https://openalex.org/W2170303799","https://openalex.org/W2171155529","https://openalex.org/W2338806053","https://openalex.org/W2407139314","https://openalex.org/W2913399920","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W2376415519","https://openalex.org/W1601381279","https://openalex.org/W4294769427","https://openalex.org/W1895908943","https://openalex.org/W4225667838","https://openalex.org/W4281893144","https://openalex.org/W2374747083","https://openalex.org/W4386270999","https://openalex.org/W4399378742","https://openalex.org/W4388254351"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,68,80,93],"design":[4],"an":[5,73,95,171],"approach":[6,18],"for":[7,14],"automatic":[8],"feature":[9,134,184],"selection":[10],"and":[11,33,59,115,123,144,150,193],"voice":[12,31],"creation":[13,32],"expressive":[15,30,42],"synthesis.":[16,43],"Our":[17],"is":[19,186],"guided":[20],"by":[21,147],"two":[22],"main":[23],"goals:":[24],"(1)":[25],"increasing":[26],"the":[27,36,61,85,90,99,126,133,142,162,189],"flexibility":[28],"of":[29,38,49,63,72,98,141,170,191],"(2)":[34],"overcoming":[35],"limitations":[37],"speaking":[39,121],"styles":[40,122],"in":[41,132,188],"We":[44,153],"define":[45],"a":[46,138,156,167],"novel":[47,157],"set":[48,185],"features,":[50],"combining":[51],"traditionally":[52],"used":[53],"prosodic":[54,114],"features":[55,58,67,117],"with":[56],"spectral":[57,116],"proposing":[60],"use":[62],"iVectors.":[64],"With":[65],"these":[66,78],"perform":[69],"unsupervised":[70,100],"clustering":[71,91,101],"audiobook":[74,145,172],"excerpt":[75,169],"and,":[76],"from":[77,177],"clusters,":[79],"create":[81],"synthetic":[82,174],"voices":[83,175],"using":[84,173],"SAT":[86],"technique.":[87],"To":[88],"evaluate":[89],"performance":[92],"propose":[94],"objective":[96,109],"evaluation":[97,110,159],"results":[102,128,180],"technique":[103],"based":[104],"on":[105],"perplexity":[106,139],"reduction.":[107],"This":[108],"indicates":[111],"that":[112,182],"both":[113],"contribute":[118],"to":[119,137,165],"separate":[120],"emotions,":[124],"achieving":[125],"best":[127],"when":[129],"including":[130],"iVectors":[131],"set,":[135],"leading":[136],"reduction":[140],"expressions":[143],"characters":[146],"factors":[148],"14":[149],"2,":[151],"respectively.":[152],"also":[154],"designed":[155],"subjective":[158],"method":[160],"where":[161],"participants":[163],"have":[164],"edit":[166],"small":[168],"created":[176],"clusters.":[178],"The":[179],"suggest":[181],"our":[183],"effective":[187],"task":[190],"expressiveness":[192],"character":[194],"detection.":[195]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}