{"id":"https://openalex.org/W4399527282","doi":"https://doi.org/10.1109/taffc.2024.3412152","title":"Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability","display_name":"Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability","publication_year":2024,"publication_date":"2024-06-11","ids":{"openalex":"https://openalex.org/W4399527282","doi":"https://doi.org/10.1109/taffc.2024.3412152"},"language":"en","primary_location":{"id":"doi:10.1109/taffc.2024.3412152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3412152","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-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/A5071414891","display_name":"J. P. Zheng","orcid":"https://orcid.org/0009-0003-2602-2910"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Zheng","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0003-2602-2910","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067137933","display_name":"Jian Zhou","orcid":"https://orcid.org/0000-0001-6509-5520"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Zhou","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6509-5520","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029771864","display_name":"Wenming Zheng","orcid":"https://orcid.org/0000-0002-7764-5179"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenming Zheng","raw_affiliation_strings":["Key Laboratory of Child Development and Learning Science (Southeast University), Ministry of Education, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7764-5179","affiliations":[{"raw_affiliation_string":"Key Laboratory of Child Development and Learning Science (Southeast University), Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709936","display_name":"Liang Tao","orcid":"https://orcid.org/0000-0001-8553-8421"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Tao","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8553-8421","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082995815","display_name":"Hon Keung Kwan","orcid":"https://orcid.org/0000-0003-0173-1625"},"institutions":[{"id":"https://openalex.org/I74413500","display_name":"University of Windsor","ror":"https://ror.org/01gw3d370","country_code":"CA","type":"education","lineage":["https://openalex.org/I74413500"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hon Keung Kwan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-0173-1625","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada","institution_ids":["https://openalex.org/I74413500"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2187,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81621019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"68","last_page":"82"},"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":0.9984999895095825,"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":0.9939000010490417,"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/generalization","display_name":"Generalization","score":0.7392277717590332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6676002740859985},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.6377006769180298},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5915218591690063},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.540791928768158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4978902339935303},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"Emotion classification","score":0.43144288659095764},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3586241602897644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29684552550315857},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2032487988471985}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7392277717590332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6676002740859985},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.6377006769180298},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5915218591690063},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.540791928768158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4978902339935303},{"id":"https://openalex.org/C206310091","wikidata":"https://www.wikidata.org/wiki/Q750859","display_name":"Emotion classification","level":2,"score":0.43144288659095764},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3586241602897644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29684552550315857},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2032487988471985},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taffc.2024.3412152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taffc.2024.3412152","pdf_url":null,"source":{"id":"https://openalex.org/S104780363","display_name":"IEEE Transactions on Affective Computing","issn_l":"1949-3045","issn":["1949-3045","2371-9850"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Affective Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5522654901","display_name":null,"funder_award_id":"61902064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8673086302","display_name":null,"funder_award_id":"1908085MF209","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W162654330","https://openalex.org/W1489323111","https://openalex.org/W1561109978","https://openalex.org/W1599408271","https://openalex.org/W1959608418","https://openalex.org/W2150791533","https://openalex.org/W2187089797","https://openalex.org/W2524985544","https://openalex.org/W2603120115","https://openalex.org/W2603777577","https://openalex.org/W2770743791","https://openalex.org/W2785364623","https://openalex.org/W2787378487","https://openalex.org/W2793479148","https://openalex.org/W2895056394","https://openalex.org/W2904459034","https://openalex.org/W2932022923","https://openalex.org/W2937870435","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2966387353","https://openalex.org/W3008691130","https://openalex.org/W3010916717","https://openalex.org/W3015645837","https://openalex.org/W3015841875","https://openalex.org/W3033411150","https://openalex.org/W3095199334","https://openalex.org/W3097003111","https://openalex.org/W3135644023","https://openalex.org/W3150572638","https://openalex.org/W3160329778","https://openalex.org/W3162791003","https://openalex.org/W3171667842","https://openalex.org/W3174758275","https://openalex.org/W3196850540","https://openalex.org/W3206725777","https://openalex.org/W4205742757","https://openalex.org/W4210433094","https://openalex.org/W4210777104","https://openalex.org/W4226421465","https://openalex.org/W4240797252","https://openalex.org/W4281562038","https://openalex.org/W4283832640","https://openalex.org/W4298839562","https://openalex.org/W6635801919","https://openalex.org/W6640963894","https://openalex.org/W6703410559","https://openalex.org/W6727420689","https://openalex.org/W6746238782","https://openalex.org/W6749555683","https://openalex.org/W6750489868","https://openalex.org/W6755082579","https://openalex.org/W6760861152","https://openalex.org/W6762643587","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6796730497","https://openalex.org/W6800440403","https://openalex.org/W6802119844","https://openalex.org/W6802591955"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"The":[0,20,56,124],"aim":[1],"of":[2,28,150,159,176],"multi-speaker":[3,52,168],"emotional":[4,18,53,76,154,169],"speech":[5,10,29,54,155,170],"synthesis":[6,156],"is":[7,22,60,108],"to":[8,25,50,73,81,110],"generate":[9],"for":[11,140],"a":[12,16,47,63,70,92],"designated":[13],"speaker":[14],"in":[15,121,167],"desired":[17],"state.":[19],"task":[21],"challenging":[23],"due":[24],"the":[26,82,129,143,147,160],"presence":[27],"variations,":[30],"such":[31],"as":[32,69,96],"noise,":[33],"content,":[34],"and":[35,42,146],"timbre,":[36],"which":[37,59,118],"can":[38,132],"obstruct":[39],"emotion":[40,67,87,100,112,126,144,148,178],"extraction":[41],"transfer.":[43],"This":[44],"paper":[45],"proposes":[46],"new":[48],"approach":[49],"performing":[51],"synthesis.":[55],"proposed":[57,109],"method,":[58],"based":[61],"on":[62],"seq2seq":[64],"synthesizer,":[65],"integrates":[66],"embedding":[68,113,127],"conditioned":[71,135],"variable":[72],"convey":[74],"exact":[75],"information":[77],"from":[78,128],"reference":[79],"audio":[80],"synthesized":[83,151],"speech.":[84,152],"To":[85],"boost":[86],"representation":[88],"capability,":[89],"we":[90],"utilize":[91],"three-dimensional":[93],"acoustic":[94],"feature":[95],"input.":[97],"And":[98],"an":[99],"generalization":[101,116,130],"module":[102,131],"with":[103,114,173],"adaptive":[104],"instance":[105],"normalization":[106],"(AdaIN)":[107],"obtain":[111],"high":[115,177],"ability,":[117],"also":[119],"results":[120,158],"improved":[122],"controllability.":[123,179],"derived":[125],"be":[133],"readily":[134],"by":[136],"affine":[137],"parameters,":[138],"allowing":[139],"control":[141],"both":[142],"category":[145],"intensity":[149],"Various":[153],"experimental":[157],"propposed":[161],"method":[162],"demonstrate":[163],"its":[164,174],"state-of-the-art":[165],"performance":[166],"synthesis,":[171],"coupled":[172],"advantage":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}