{"id":"https://openalex.org/W2279599233","doi":"https://doi.org/10.1109/coginfocom.2015.7390589","title":"Synthesis of speaking styles with corpus- and HMM-based approaches","display_name":"Synthesis of speaking styles with corpus- and HMM-based approaches","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2279599233","doi":"https://doi.org/10.1109/coginfocom.2015.7390589","mag":"2279599233"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2015.7390589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2015.7390589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066613616","display_name":"P\u00e9ter R. Nagy","orcid":"https://orcid.org/0000-0001-6692-0879"},"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":true,"raw_author_name":"Peter Nagy","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology an Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology an Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031237235","display_name":"Csaba Zaink\u00f3","orcid":null},"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":"Csaba Zainko","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology an Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology an Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069988513","display_name":"G\u00e9za N\u00e9meth","orcid":"https://orcid.org/0000-0002-2311-4858"},"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":"Geza Nemeth","raw_affiliation_strings":["Department of Telecommunications and Media Informatics, Budapest University of Technology an Economics, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"Department of Telecommunications and Media Informatics, Budapest University of Technology an Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066613616"],"corresponding_institution_ids":["https://openalex.org/I29770179"],"apc_list":null,"apc_paid":null,"fwci":0.4314,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77750214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"200"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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":0.9934999942779541,"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/naturalness","display_name":"Naturalness","score":0.8953458070755005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7229548692703247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6539932489395142},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6236450672149658},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6215987801551819},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5860005021095276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5419931411743164},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5212072134017944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4268658459186554},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4178796410560608},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41090285778045654},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14243444800376892}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8953458070755005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229548692703247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6539932489395142},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6236450672149658},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6215987801551819},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5860005021095276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5419931411743164},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5212072134017944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268658459186554},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4178796410560608},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41090285778045654},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14243444800376892},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":1,"locations":[{"id":"doi:10.1109/coginfocom.2015.7390589","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2015.7390589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"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":38,"referenced_works":["https://openalex.org/W96790560","https://openalex.org/W128592858","https://openalex.org/W129217914","https://openalex.org/W133559434","https://openalex.org/W168929619","https://openalex.org/W1513431614","https://openalex.org/W1546776967","https://openalex.org/W1564152904","https://openalex.org/W1572730534","https://openalex.org/W1965498887","https://openalex.org/W2049686551","https://openalex.org/W2058091487","https://openalex.org/W2077307609","https://openalex.org/W2087110403","https://openalex.org/W2111284386","https://openalex.org/W2119929864","https://openalex.org/W2129142580","https://openalex.org/W2129703931","https://openalex.org/W2150000736","https://openalex.org/W2150658333","https://openalex.org/W2153914468","https://openalex.org/W2166823384","https://openalex.org/W2185859000","https://openalex.org/W2296995941","https://openalex.org/W2341286996","https://openalex.org/W2408492347","https://openalex.org/W2541983972","https://openalex.org/W2606268809","https://openalex.org/W4285719527","https://openalex.org/W6603933070","https://openalex.org/W6605232188","https://openalex.org/W6605419763","https://openalex.org/W6606861284","https://openalex.org/W6633741138","https://openalex.org/W6684457288","https://openalex.org/W6686508619","https://openalex.org/W6736661190","https://openalex.org/W6865107258"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256"],"abstract_inverted_index":{"In":[0,88],"this":[1],"paper":[2],"we":[3,92],"compare":[4],"two":[5],"state-of-the-art":[6],"speech":[7,17,57,132],"synthesis":[8],"techniques":[9,122],"(corpus-":[10],"and":[11,29,53,65,80,110,133],"HMM-based)":[12],"in":[13,74,145],"terms":[14],"of":[15,84,115,130,147],"expressive":[16,56,131],"synthesis.":[18],"Two":[19],"corpora":[20,52],"were":[21,59,123],"composed":[22],"with":[23],"different":[24,46],"speaking":[25,101,141],"styles":[26],"(broadcast":[27],"news":[28],"literature":[30],"reading)":[31],"from":[32],"the":[33,45,54,85,100,116,127,137,140],"same":[34],"female":[35],"speaker.":[36],"Our":[37,113],"aim":[38],"was":[39,71,143],"to":[40,42,76,125],"determine":[41],"what":[43],"extent":[44],"technologies":[47],"reproduce":[48],"these":[49],"styles.":[50],"The":[51],"synthetic":[55],"samples":[58],"evaluated":[60],"based":[61],"on":[62,94],"objective":[63,90],"measures,":[64],"a":[66],"carefully":[67],"designed":[68],"perceptual":[69,117],"test":[70,118],"carried":[72],"out":[73],"order":[75],"evaluate":[77],"naturalness,":[78],"quality":[79],"style":[81,142],"identification":[82],"rates":[83],"generated":[86],"samples.":[87],"our":[89],"assessment":[91],"focused":[93],"prosodic":[95],"features":[96,129],"that":[97,120],"principally":[98],"influence":[99],"style:":[102],"F":[103],"<sub":[104],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[106],"contour,":[107],"average":[108],"values":[109],"articulatory":[111],"speed.":[112],"evaluation":[114],"shows":[119],"both":[121,148],"able":[124],"capture":[126],"main":[128],"although":[134],"listeners":[135],"preferred":[136],"HMM-based":[138],"voice,":[139],"recognizable":[144],"case":[146],"methods.":[149]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}