{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:30:58Z","timestamp":1783528258331,"version":"3.55.0"},"reference-count":138,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100005049","name":"Science and Engineering Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Robotics Program","award":["192 25 00054"],"award-info":[{"award-number":["192 25 00054"]}]},{"name":"Human-Robot Collaborative AI","award":["A18A2b0046"],"award-info":[{"award-number":["A18A2b0046"]}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG-100E-2018-006"],"award-info":[{"award-number":["AISG-100E-2018-006"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Big Data Computing"},{"DOI":"10.13039\/501100004853","name":"Chinese University of Hong Kong","doi-asserted-by":"publisher","award":["B10120210117-KP02"],"award-info":[{"award-number":["B10120210117-KP02"]}],"id":[{"id":"10.13039\/501100004853","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Foundation of Guangdong Province","award":["2019A050505001"],"award-info":[{"award-number":["2019A050505001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271432"],"award-info":[{"award-number":["62271432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/taffc.2022.3233324","type":"journal-article","created":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T13:57:43Z","timestamp":1672408663000},"page":"3120-3134","source":"Crossref","is-referenced-by-count":51,"title":["Speech Synthesis With Mixed Emotions"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7869-4474","authenticated-orcid":false,"given":"Kun","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8078-3305","authenticated-orcid":false,"given":"Berrak","family":"Sisman","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0506-2409","authenticated-orcid":false,"given":"Rajib","family":"Rana","sequence":"additional","affiliation":[{"name":"University of Southern Queensland, Toowoomba, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"GLAM – the Group on Language, Audio, & Music, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, and the School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0103940"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/spc3.12108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1037\/a0021846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-150"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-3129-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0329-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6627-1_2"},{"key":"ref8","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref9","volume-title":"Progress in Speech Synthesis","author":"Van Santen","year":"2013"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref11","article-title":"Char2wav: End-to-end speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Sotelo"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref13","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472730"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.3620963"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224415"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-116"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.11.004"},{"key":"ref21","volume-title":"The Emotions","author":"Plutchik","year":"1991"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.20396\/joss.v1i1.15014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-558"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-676"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288797"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-661"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-984"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282282"},{"key":"ref32","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Skerry-Ryan"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref34","article-title":"Emotional end-to-end neural speech synthesizer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29516-5_5"},{"key":"ref36","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cobeha.2017.05.016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.00428"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.121208.131605"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511499951"},{"key":"ref42","volume-title":"The Nature of Emotion: Fundamental Questions","author":"Ekman","year":"1994"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1511\/2001.28.344"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1037\/10366-003"},{"key":"ref45","volume-title":"Changing Minds: The Go-to Guide to Mental Health for Family and Friends","author":"Cross","year":"2016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273608"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2879512"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2021.3127390"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.01.003"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683273"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39857-8_15"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1052"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593944"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2352268"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344627"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1432"},{"key":"ref57","article-title":"A siamese neural network with modified distance loss for transfer learning in speech emotion recognition","author":"Feng","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2022.3175578"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref63","article-title":"Char2wav: End-to-end speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations, Workshop","author":"Kyle"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1177\/1754073919898526"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-781"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-285"},{"key":"ref67","first-page":"3693","article-title":"Adjusting pleasure-arousal-dominance for continuous emotional text-to-speech synthesizer","volume-title":"Proc. INTERSPEECH Conf.","author":"Rabiee"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref70","article-title":"Neural TTS stylization with adversarial and collaborative games","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746654"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2228"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-781"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3065460"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2002-1"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1129"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref82","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref84","first-page":"3331","article-title":"Chive: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kenter"},{"key":"ref85","article-title":"The complexity of intensity: Issues concerning the structure of emotion intensity","author":"Frijda","year":"1992"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2064"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-11"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.2466\/pms.1986.63.3.1156"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876118"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248026"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-013-0349-3"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.340"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.5.1155"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1357"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066047"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682589"},{"key":"ref105","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ping"},{"key":"ref106","article-title":"Close to human quality tts with transformer","author":"Li","year":"2018"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004008"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1066"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3034994"},{"key":"ref110","article-title":"The festival speech synthesis system, version 1.4.2","author":"Black","year":"2001"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-36"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref114","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Veaux","year":"2016"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref117","article-title":"Adam: Amethod for stochastic optimization","author":"Kingma"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273610"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053581"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/394083"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.02.010"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.1986.01800030098011"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195169157.003.0016"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383526"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1086\/338206"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1037\/a0018430"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1080\/02699931.2015.1056107"},{"issue":"8","key":"ref134","first-page":"651","article-title":"Emotion models: A review","volume":"10","author":"PS","year":"2017","journal-title":"Int. J. Control Theory Appl."},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1037\/h0043158"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1080\/026999398379574"},{"key":"ref137","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. Int. Conf. Mach. Deep Learn. Workshop","author":"Koch"},{"key":"ref138","first-page":"775","article-title":"Metric learning to rank","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"McFee"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10330166\/10003644.pdf?arnumber=10003644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T17:50:17Z","timestamp":1760982617000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10003644\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":138,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2022.3233324","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,1]]}}}