{"id":"https://openalex.org/W2921951278","doi":"https://doi.org/10.23919/apsipa.2018.8659599","title":"A DNN-based emotional speech synthesis by speaker adaptation","display_name":"A DNN-based emotional speech synthesis by speaker adaptation","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921951278","doi":"https://doi.org/10.23919/apsipa.2018.8659599","mag":"2921951278"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659599","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/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":true,"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":"middle","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":false,"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":"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/A5032919424"],"corresponding_institution_ids":["https://openalex.org/I68986083"],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80616266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"633","last_page":"637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9955999851226807,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8286533951759338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8190079927444458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686595916748047},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7645664215087891},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5732365846633911},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.543161928653717},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5382556319236755},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5021858215332031},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.48921632766723633},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4823136329650879},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.43342283368110657},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4149845242500305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40516117215156555},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1217484176158905},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06068974733352661}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8286533951759338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8190079927444458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686595916748047},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7645664215087891},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5732365846633911},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.543161928653717},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5382556319236755},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5021858215332031},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.48921632766723633},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4823136329650879},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43342283368110657},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4149845242500305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40516117215156555},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1217484176158905},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06068974733352661},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659599","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659599","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"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/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2098421901","https://openalex.org/W2102146461","https://openalex.org/W2105698384","https://openalex.org/W2129142580","https://openalex.org/W2153914468","https://openalex.org/W2533395159","https://openalex.org/W2598638573","https://openalex.org/W2737658251","https://openalex.org/W2785364623","https://openalex.org/W2787378487","https://openalex.org/W2963927338","https://openalex.org/W4295731579","https://openalex.org/W6606720608","https://openalex.org/W6639984793"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W4200068392"],"abstract_inverted_index":{"The":[0,102],"paper":[1],"proposes":[2],"a":[3,24,31,58,87],"deep":[4],"neural":[5],"network":[6],"(DNN)-based":[7],"emotional":[8,18,99,104,143,161,181],"speech":[9,19,28,77,105,144,156,162],"synthesis":[10],"method":[11,129,149,171],"to":[12,36,49,85,153],"improve":[13,173],"the":[14,38,44,51,69,80,109,120,127,139,142,147,154,160,165,169,174],"quality":[15],"of":[16,60,75,89,94,141,159,179],"synthesized":[17,107,145,163,180],"by":[20,108,146,164],"speaker":[21,81],"adaptation":[22,82],"with":[23,68,97,119],"multi-speaker":[25],"and":[26,72,177],"multi-emotion":[27,76],"corpus.":[29,78],"Firstly,":[30],"text":[32],"analyzer":[33],"is":[34,47,83,106,150],"employed":[35],"obtain":[37],"contextual":[39,70],"labels":[40,71],"from":[41,54],"sentences":[42],"while":[43],"WORLD":[45],"vocoder":[46],"used":[48],"extract":[50],"acoustic":[52,73],"features":[53,74],"corresponding":[55],"speeches.":[56,101],"Then":[57],"set":[59,88],"speaker-independent":[61],"DNN":[62,91,111],"average":[63],"voice":[64,92,112],"models":[65,93],"are":[66],"trained":[67],"Finally,":[79],"adopted":[84],"train":[86],"speaker-dependent":[90,110],"target":[95,98,103],"emotion":[96,175],"training":[100],"models.":[113],"Subjective":[114],"evaluations":[115],"show":[116],"that":[117,138,158],"comparing":[118],"traditional":[121],"hidden":[122],"Markov":[123],"model":[124],"(HMM)-based":[125],"method,":[126],"proposed":[128,148,170],"can":[130,172],"achieve":[131],"higher":[132],"opinion":[133],"scores.":[134],"Objective":[135],"tests":[136],"demonstrate":[137],"spectrum":[140],"also":[151],"closer":[152],"original":[155],"than":[157],"HMM-based":[166],"method.":[167],"Therefore,":[168],"express":[176],"naturalness":[178],"speech.":[182]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}