{"id":"https://openalex.org/W2576799197","doi":"https://doi.org/10.1109/apsipa.2016.7820690","title":"Voice conversion to emotional speech based on three-layered model in dimensional approach and parameterization of dynamic features in prosody","display_name":"Voice conversion to emotional speech based on three-layered model in dimensional approach and parameterization of dynamic features in prosody","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2576799197","doi":"https://doi.org/10.1109/apsipa.2016.7820690","mag":"2576799197"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2016.7820690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5101012633","display_name":"Yawen Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yawen Xue","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038532837","display_name":"Yasuhiro Hamada","orcid":"https://orcid.org/0000-0001-6448-9050"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiro Hamada","raw_affiliation_strings":["Meiji University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Meiji University, Tokyo, Japan","institution_ids":["https://openalex.org/I16656306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055059119","display_name":"Masato Akagi","orcid":"https://orcid.org/0000-0003-2450-6754"},"institutions":[{"id":"https://openalex.org/I177738480","display_name":"Japan Advanced Institute of Science and Technology","ror":"https://ror.org/03frj4r98","country_code":"JP","type":"education","lineage":["https://openalex.org/I177738480"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Akagi","raw_affiliation_strings":["Japan Advanced Institute of Science and Technology, Ishikawa, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Advanced Institute of Science and Technology, Ishikawa, Japan","institution_ids":["https://openalex.org/I177738480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101012633"],"corresponding_institution_ids":["https://openalex.org/I177738480"],"apc_list":null,"apc_paid":null,"fwci":0.5094,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67543192,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"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/T11309","display_name":"Music and Audio Processing","score":0.9861000180244446,"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/prosody","display_name":"Prosody","score":0.8259478807449341},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7560600638389587},{"id":"https://openalex.org/keywords/emotional-prosody","display_name":"Emotional prosody","score":0.7031272053718567},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6515120267868042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6406546831130981},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6075401306152344},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4962823987007141},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"Emotional expression","score":0.45284193754196167},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.42391538619995117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3525863587856293},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24873319268226624},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.19297653436660767},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12517693638801575}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8259478807449341},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7560600638389587},{"id":"https://openalex.org/C2778262033","wikidata":"https://www.wikidata.org/wiki/Q5373795","display_name":"Emotional prosody","level":3,"score":0.7031272053718567},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6515120267868042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406546831130981},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6075401306152344},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4962823987007141},{"id":"https://openalex.org/C143110190","wikidata":"https://www.wikidata.org/wiki/Q5373787","display_name":"Emotional expression","level":2,"score":0.45284193754196167},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.42391538619995117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3525863587856293},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24873319268226624},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.19297653436660767},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12517693638801575},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipa.2016.7820690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.jaist.ac.jp:10119/14281","is_oa":false,"landing_page_url":"http://hdl.handle.net/10119/14281","pdf_url":null,"source":{"id":"https://openalex.org/S4406922663","display_name":"JAIST Repository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W179271164","https://openalex.org/W1603461030","https://openalex.org/W1849169576","https://openalex.org/W1974843131","https://openalex.org/W1996368127","https://openalex.org/W2002268800","https://openalex.org/W2019207321","https://openalex.org/W2030516049","https://openalex.org/W2042360461","https://openalex.org/W2048960384","https://openalex.org/W2049686551","https://openalex.org/W2077726817","https://openalex.org/W2078154198","https://openalex.org/W2084969212","https://openalex.org/W2117418893","https://openalex.org/W2129703931","https://openalex.org/W2149425161","https://openalex.org/W2150791533","https://openalex.org/W2291613313","https://openalex.org/W3044514286","https://openalex.org/W6781138257"],"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/W2024201202"],"abstract_inverted_index":{"This":[0,189],"paper":[1],"proposes":[2],"a":[3,78,81,99,122],"system":[4,194],"to":[5,9,65,94,102,126,134,152,200],"convert":[6,141],"neutral":[7],"speech":[8,59,113,119,133,144,203],"emotional":[10,23,36,50,58,112,138,185,202,213],"with":[11,87,181],"controlled":[12],"intensity":[13,53,186,214],"of":[14,17,22,105,109,116,130,184,212],"emotions.":[15],"Most":[16],"previous":[18],"researches":[19],"considering":[20],"synthesis":[21],"voices":[24],"used":[25],"statistical":[26],"or":[27,48],"concatenative":[28],"methods":[29,151],"that":[30,115,158,175,192],"can":[31,74,84,177,208],"synthesize":[32,135,201],"emotions":[33,86],"in":[34,60,80,156,204,215,219],"categorical":[35],"states":[37,51],"such":[38],"as":[39,77],"joy,":[40],"angry,":[41],"sad,":[42],"etc.":[43],"While":[44],"humans":[45],"sometimes":[46],"enhance":[47],"relieve":[49],"and":[52,120,146,165,187],"during":[54],"daily":[55],"life,":[56],"synthesized":[57],"categories":[61],"is":[62],"not":[63,195],"enough":[64],"describe":[66,95],"these":[67],"phenomena":[68],"precisely.":[69],"A":[70],"dimensional":[71,82,92,216],"approach":[72,93],"which":[73],"represent":[75],"emotion":[76,180,222],"point":[79],"space":[83,217],"express":[85],"continuous":[88],"intensity.":[89],"Employing":[90],"the":[91,106,110,136,142,198,210,220],"emotion,":[96],"we":[97,148],"conduct":[98],"three-layered":[100],"model":[101,161,168],"estimate":[103],"displacement":[104],"acoustic":[107,128],"features":[108,129,155],"target":[111,137,166],"from":[114],"source":[117,131,143],"(neutral)":[118,132],"propose":[121],"rule-based":[123],"conversion":[124],"method":[125],"modify":[127],"speech.":[139],"To":[140],"freely":[145],"easily,":[147],"introduce":[149],"two":[150],"parameterize":[153],"dynamic":[154],"prosody,":[157],"is,":[159],"Fujisaki":[160],"for":[162,169],"f0":[163],"contour":[164],"prediction":[167],"power":[170],"envelope.":[171],"Evaluation":[172],"results":[173],"show":[174],"subjects":[176],"perceive":[178],"intended":[179],"satisfactory":[182],"order":[183,211],"naturalness.":[188],"fact":[190],"means":[191],"this":[193],"only":[196],"has":[197],"ability":[199],"category":[205],"but":[206],"also":[207],"control":[209],"even":[218],"same":[221],"category.":[223]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}