{"id":"https://openalex.org/W2015687745","doi":"https://doi.org/10.1109/slt.2012.6424239","title":"Synthesizing expressive speech from amateur audiobook recordings","display_name":"Synthesizing expressive speech from amateur audiobook recordings","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2015687745","doi":"https://doi.org/10.1109/slt.2012.6424239","mag":"2015687745"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","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-185533","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063795282","display_name":"\u00c9va Sz\u00e9kely","orcid":"https://orcid.org/0000-0003-1175-840X"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Eva Szekely","raw_affiliation_strings":["CNGL, School of Computer Science and Informatics, University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"CNGL, School of Computer Science and Informatics, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tamas Gabor Csapo","raw_affiliation_strings":["Department of Telecommunication and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","Dept. of Telecommunication and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunication and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Dept. of Telecommunication and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783073","display_name":"B\u00e1lint T\u00f3th","orcid":"https://orcid.org/0000-0003-1688-9089"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Balint Toth","raw_affiliation_strings":["Department of Telecommunication and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","Dept. of Telecommunication and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunication and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Dept. of Telecommunication and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020514527","display_name":"P\u00e9ter Mihajlik","orcid":"https://orcid.org/0000-0001-7532-9773"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Peter Mihajlik","raw_affiliation_strings":["Department of Telecommunication and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","Dept. of Telecommunication and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunication and Media Informatics, Budapest University\u00a0of\u00a0Technology\u00a0and\u00a0Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Dept. of Telecommunication and Media Informatics, Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046306415","display_name":"Julie Carson-Berndsen","orcid":"https://orcid.org/0000-0002-1851-3643"},"institutions":[{"id":"https://openalex.org/I100930933","display_name":"University College Dublin","ror":"https://ror.org/05m7pjf47","country_code":"IE","type":"education","lineage":["https://openalex.org/I100930933"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Julie Carson-Berndsen","raw_affiliation_strings":["CNGL, School of Computer Science and Informatics, University College Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"CNGL, School of Computer Science and Informatics, University College Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I100930933"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063795282"],"corresponding_institution_ids":["https://openalex.org/I100930933"],"apc_list":null,"apc_paid":null,"fwci":3.9779,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93562691,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"6","issue":null,"first_page":"297","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7515783309936523},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6835669875144958},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6788671016693115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6640479564666748},{"id":"https://openalex.org/keywords/amateur","display_name":"Amateur","score":0.6359632611274719},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5040889978408813},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1625324785709381},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.13625425100326538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7515783309936523},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6835669875144958},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6788671016693115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6640479564666748},{"id":"https://openalex.org/C2778044066","wikidata":"https://www.wikidata.org/wiki/Q455595","display_name":"Amateur","level":2,"score":0.6359632611274719},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5040889978408813},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1625324785709381},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.13625425100326538},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2012.6424239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:kth-185533","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-185533","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":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:kth-185533","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-185533","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":"","raw_type":"Conference paper"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W62174847","https://openalex.org/W129217914","https://openalex.org/W169745891","https://openalex.org/W1486631742","https://openalex.org/W1517939602","https://openalex.org/W1589081167","https://openalex.org/W1631260214","https://openalex.org/W1756939916","https://openalex.org/W2049686551","https://openalex.org/W2121299803","https://openalex.org/W2132039819","https://openalex.org/W2156146072","https://openalex.org/W2159290663","https://openalex.org/W2251812144","https://openalex.org/W2294232014","https://openalex.org/W2396127172","https://openalex.org/W2399786064","https://openalex.org/W2401838240","https://openalex.org/W6602559115","https://openalex.org/W6605232188","https://openalex.org/W6636811518","https://openalex.org/W6637893649","https://openalex.org/W6683445396","https://openalex.org/W6712575894","https://openalex.org/W6713426374"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"Freely":[0],"available":[1,50,182],"audiobooks":[2,31,180],"are":[3,53,58],"a":[4,42,81,98,158],"rich":[5],"resource":[6],"of":[7,18,36,48,73,101,115,161],"expressive":[8,23,38,63,78,116,121,138],"speech":[9,19,39,69,79,117,140,162],"recordings":[10],"that":[11,32,136,171],"can":[12],"be":[13],"used":[14,157],"for":[15,123],"the":[16,107,110,137,172],"purposes":[17],"synthesis.":[20],"Natural":[21],"sounding,":[22],"synthetic":[24,139],"voices":[25,122],"have":[26,134],"previously":[27],"been":[28],"built":[29],"from":[30,41,80],"contained":[33],"large":[34],"amounts":[35],"highly":[37],"recorded":[40,111],"professionally":[43],"trained":[44],"speaker.":[45],"The":[46],"majority":[47],"freely":[49],"audiobooks,":[51],"however,":[52],"read":[54],"by":[55,96],"amateur":[56],"speakers,":[57],"shorter":[59],"and":[60,75,119],"contain":[61],"less":[62,66],"(less":[64],"emphatic,":[65],"emotional,":[67],"etc.)":[68],"both":[70],"in":[71,164,167],"terms":[72],"quality":[74],"quantity.":[76],"Synthesizing":[77],"typical":[82,179],"online":[83],"audiobook":[84],"therefore":[85],"poses":[86],"many":[87],"challenges.":[88],"In":[89],"this":[90,143],"work":[91],"we":[92],"address":[93],"these":[94],"challenges":[95],"applying":[97],"method":[99,144,173],"consisting":[100],"minimally":[102],"supervised":[103],"techniques":[104],"to":[105,148,152,169,177],"align":[106],"text":[108],"with":[109,142],"speech,":[112],"select":[113],"groups":[114],"segments":[118],"build":[120],"hidden":[124],"Markov-model":[125],"based":[126],"synthesis":[127],"using":[128],"speaker":[129],"adaptation.":[130],"Subjective":[131],"listening":[132],"tests":[133],"shown":[135],"generated":[141],"is":[145,174],"often":[146],"able":[147],"produce":[149],"utterances":[150],"suited":[151],"an":[153],"emotional":[154],"message.":[155],"We":[156],"restricted":[159],"amount":[160],"data":[163],"our":[165],"experiment,":[166],"order":[168],"show":[170],"generally":[175],"applicable":[176],"most":[178],"widely":[181],"online.":[183]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
