{"id":"https://openalex.org/W2944514397","doi":"https://doi.org/10.1109/iscslp.2018.8706656","title":"Emotional speech synthesis based on DNN and PAD emotional state model","display_name":"Emotional speech synthesis based on DNN and PAD emotional state model","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944514397","doi":"https://doi.org/10.1109/iscslp.2018.8706656","mag":"2944514397"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706656","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/A5060794156","display_name":"Weizhao Zhang","orcid":"https://orcid.org/0000-0002-3692-4921"},"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":"Weizhao ZHANG","raw_affiliation_strings":["College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","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":["College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088475907","display_name":"Pengpeng Zhi","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":false,"raw_author_name":"Pengpeng ZHI","raw_affiliation_strings":["College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060794156"],"corresponding_institution_ids":["https://openalex.org/I68986083"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.21478903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2018","issue":null,"first_page":"41","last_page":"45"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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":0.9829000234603882,"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":0.7852328419685364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380824685096741},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7275718450546265},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5523543953895569},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5498155355453491},{"id":"https://openalex.org/keywords/arousal","display_name":"Arousal","score":0.4967525601387024},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.45123088359832764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4056154489517212},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17337307333946228},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10677960515022278}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7852328419685364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380824685096741},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7275718450546265},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5523543953895569},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5498155355453491},{"id":"https://openalex.org/C36951298","wikidata":"https://www.wikidata.org/wiki/Q379784","display_name":"Arousal","level":2,"score":0.4967525601387024},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.45123088359832764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4056154489517212},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17337307333946228},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10677960515022278},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp.2018.8706656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706656","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"},{"id":"mag:3162510810","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902219172667326","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W165351933","https://openalex.org/W1492383498","https://openalex.org/W1912941063","https://openalex.org/W1963778986","https://openalex.org/W2039143993","https://openalex.org/W2039800941","https://openalex.org/W2043003570","https://openalex.org/W2043181832","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2098421901","https://openalex.org/W2102146461","https://openalex.org/W2105698384","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2153914468","https://openalex.org/W2785364623","https://openalex.org/W6606720608","https://openalex.org/W6629609042","https://openalex.org/W6640989505"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W175280642"],"abstract_inverted_index":{"An":[0],"emotional":[1,14,28,43,51,56,83,120],"speech":[2,34,46,57,73,84,121],"synthesis":[3,58],"method":[4,59,106,126],"based":[5],"on":[6],"deep":[7],"neural":[8],"network":[9],"(DNN)":[10],"and":[11,32,48,101],"Pleasure-Arousal-Dominance":[12],"(PAD)":[13],"state":[15,29],"model":[16,22,99],"is":[17,23,60,85,127],"proposed.":[18],"Firstly,":[19],"the":[20,27,38,41,49,54,67,81,104,116,119,124,131],"PAD":[21,78],"used":[24,61],"to":[25,62,130],"annotate":[26],"of":[30,45,70,118],"multi-speaker":[31],"multi-emotion":[33],"corpus":[35,47],"by":[36,76,87,123],"calculating":[37],"distance":[39],"between":[40],"marked":[42],"point":[44],"typical":[50],"point.":[52],"Secondly,":[53],"DNN-based":[55,102],"generate":[63],"acoustic":[64],"features.":[65],"Thirdly,":[66],"prosodic":[68],"features":[69],"synthesized":[71,86,122],"emotion":[72],"are":[74],"modified":[75],"using":[77],"model.":[79],"Finally,":[80],"target":[82],"vocoder.":[88],"The":[89],"subjective":[90],"evaluation":[91],"results":[92],"show":[93],"that":[94,115],"comparing":[95],"with":[96],"hidden":[97],"Markov":[98],"(HMM)-based":[100],"method,":[103],"proposed":[105,125],"can":[107],"achieve":[108],"better":[109],"performance.":[110],"Objective":[111],"tests":[112],"also":[113],"demonstrate":[114],"spectrum":[117],"much":[128],"closer":[129],"original":[132],"speech.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}