{"id":"https://openalex.org/W2944152828","doi":"https://doi.org/10.1109/iscslp.2018.8706693","title":"A Method for Emotional Speech Synthesis Based on Speaker Adaptive Training","display_name":"A Method for Emotional Speech Synthesis Based on Speaker Adaptive Training","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944152828","doi":"https://doi.org/10.1109/iscslp.2018.8706693","mag":"2944152828"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5112306287","display_name":"Xiaoyong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyong Lu","raw_affiliation_strings":["School of Psychology, Northwest Normal University, China"],"affiliations":[{"raw_affiliation_string":"School of Psychology, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642426","display_name":"Yanqin Li","orcid":"https://orcid.org/0000-0002-8709-8201"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanqin Li","raw_affiliation_strings":["School of Physics and Electronic Engineering, Northwest Normal University, China"],"affiliations":[{"raw_affiliation_string":"School of Physics and Electronic Engineering, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032919424","display_name":"Hongwu Yang","orcid":"https://orcid.org/0000-0002-8939-3386"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwu Yang","raw_affiliation_strings":["School of Physics and Electronic Engineering, Northwest Normal University, China"],"affiliations":[{"raw_affiliation_string":"School of Physics and Electronic Engineering, Northwest Normal University, China","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112306287"],"corresponding_institution_ids":["https://openalex.org/I68986083"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21380407,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9783999919891357,"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":0.9728000164031982,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8863146305084229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8026716709136963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7777206897735596},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5425323843955994},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5380930304527283},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5251262784004211},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5125529766082764},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47222402691841125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46216699481010437},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4552428424358368},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43580374121665955},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.423012912273407},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42101404070854187},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14997181296348572},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1371835172176361}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8863146305084229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026716709136963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7777206897735596},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5425323843955994},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5380930304527283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5251262784004211},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5125529766082764},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47222402691841125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46216699481010437},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4552428424358368},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43580374121665955},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.423012912273407},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42101404070854187},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14997181296348572},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1371835172176361},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706693","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706693","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1572989473","https://openalex.org/W1823609680","https://openalex.org/W1995565802","https://openalex.org/W2036740752","https://openalex.org/W2057891540","https://openalex.org/W2111284386","https://openalex.org/W2114010348","https://openalex.org/W2115052578","https://openalex.org/W2139751012","https://openalex.org/W2153914468","https://openalex.org/W2200649065","https://openalex.org/W2326809952","https://openalex.org/W2753741845","https://openalex.org/W6665048022","https://openalex.org/W6677306394"],"related_works":["https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2152945827","https://openalex.org/W1909292483"],"abstract_inverted_index":{"Emotional":[0],"speech":[1,9,19,31,36,66],"synthesis":[2,32,37,67],"is":[3,44,54,69,100,143],"expected":[4],"to":[5,14,26,46,71,102,107],"make":[6],"the":[7,91,96,103,120,128,131,137],"synthesized":[8],"more":[10,16],"expressive.":[11],"In":[12],"order":[13],"synthesize":[15],"natural":[17],"emotional":[18,30,48,58,87,111,122,134],"signals,":[20],"this":[21,124],"paper":[22],"presents":[23],"a":[24,34,78,85,109],"method":[25,125,129],"realize":[27],"HMM":[28],"based":[29],"using":[33,90,130],"Mandarin":[35,40,51,65,80,141],"framework.":[38],"A":[39,50,64],"context-dependent":[41],"label":[42,47],"format":[43],"adopted":[45],"sentences.":[49],"question":[52],"set":[53],"also":[55],"extended":[56],"for":[57],"sentences":[59],"by":[60],"adding":[61],"language-specific":[62],"questions.":[63],"framework":[68],"utilized":[70],"train":[72],"an":[73],"average":[74,104],"voice":[75,105],"model":[76,106,135],"from":[77],"large":[79],"multi":[81],"speaker-based":[82],"corpus":[83,89],"and":[84],"small":[86],"one-speaker-based":[88],"Speaker":[92],"Adaptive":[93],"Training.":[94],"Then":[95],"speaker":[97,132],"adaptation":[98],"transformation":[99],"applied":[101],"obtain":[108],"speaker-adapted":[110],"model.":[112],"Experimental":[113],"results":[114],"show":[115],"that":[116],"in":[117],"case":[118],"of":[119,139],"same":[121],"corpus,":[123],"proposed":[126],"outperforms":[127],"dependent":[133],"when":[136],"number":[138],"training":[140],"utterances":[142],"increased.":[144]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}