{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T02:12:02Z","timestamp":1784945522371,"version":"3.55.0"},"reference-count":137,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Science and Engineering Research Council, Agency of Science, Technology and Research"},{"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"}]},{"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":"RIE2020 Advanced Manufacturing and Engineering Domain","award":["A1687b0033"],"award-info":[{"award-number":["A1687b0033"]}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-T2EP50220-0021"],"award-info":[{"award-number":["MOE-T2EP50220-0021"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SUTD Start-up Grant Artificial Intelligence for Human Voice Conversion","award":["SRG ISTD 2020 158"],"award-info":[{"award-number":["SRG ISTD 2020 158"]}]},{"name":"SUTD AI Grant &#x2013; Thrust 2 Discovery by AI","award":["SGPAIRS1821"],"award-info":[{"award-number":["SGPAIRS1821"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/taffc.2022.3175578","type":"journal-article","created":{"date-parts":[[2022,5,19]],"date-time":"2022-05-19T20:31:29Z","timestamp":1652992289000},"page":"31-48","source":"Crossref","is-referenced-by-count":63,"title":["Emotion Intensity and its Control for Emotional Voice Conversion"],"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":"Singapore University of Technology and Design, Singapore"}],"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 &#x2013; The Group on Language, Audio, and 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":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-3129-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0329-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-6627-1_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3038524"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5772\/2391"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CCPR.2009.5344042"},{"key":"ref9","first-page":"617","article-title":"Happiness","author":"Averill","year":"1993","journal-title":"Handbook of Emotions"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/2158244016658084"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1207\/s15327957pspr0301_1"},{"key":"ref12","article-title":"The complexity of intensity: Issues concerning the structure of emotion intensity","volume":"13","author":"Frijda","year":"1992","journal-title":"Rev. Pers. Social Psychol."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1620853.1620878"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2011-771"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2064"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-11"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3065460"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-661"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041640"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-984"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1325"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383526"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2878"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1323"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref36","article-title":"Char2Wav: End-to-end speech synthesis","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Sotelo"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3047262"},{"key":"ref41","article-title":"Textless speech emotion conversion using decomposed and discrete representations","author":"Kreuk","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683865"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053255"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.2466\/pms.1986.63.3.1156"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/02699939208411068"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1037\/1528-3542.1.4.381"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2860246"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001456"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413973"},{"key":"ref53","article-title":"FastS2S-VC: Streaming non-autoregressive sequence-to-sequence voice conversion","author":"Kameoka","year":"2021"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049336"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076867"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682380"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-285"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-781"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/S1071-5819(02)00141-6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1250\/ast.26.317"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178817"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-171"},{"key":"ref65","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":"ref66","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":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1129"},{"key":"ref71","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref73","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":"ref74","doi-asserted-by":"publisher","DOI":"10.1121\/1.405558"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.20396\/joss.v1i1.15014"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2828429"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2955949"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683077"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1177\/1754073919898526"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2021.3114365"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3069"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3129340"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1236"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(01)00024-3"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-11"},{"key":"ref93","first-page":"433","article-title":"Learning visual attributes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ferrari"},{"key":"ref94","first-page":"775","article-title":"Metric learning to rank","volume-title":"Proc. 27th Int. Conf. Mach. Learn.","author":"McFee"},{"key":"ref95","article-title":"Siamese neural networks for one-shot image recognition","volume-title":"Proc. ICML deep Learn. Workshop","author":"Koch"},{"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":"10.1109\/LSP.2020.3036349"},{"key":"ref102","article-title":"The CMU arctic speech databases","volume-title":"Proc. 5th ISCA Workshop Speech Synth.","author":"Kominek"},{"key":"ref103","article-title":"The LJ speech dataset","author":"Ito","year":"2017"},{"key":"ref104","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit","author":"Christophe","year":"2016","journal-title":"Centre Speech Technol. Res."},{"key":"ref105","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord"},{"issue":"Nov","key":"ref107","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1114856"},{"key":"ref109","volume-title":"Algorithms for Clustering Data","author":"Jain","year":"1988"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.21236\/ADA439551"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1002\/9781118874059"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.35"},{"key":"ref113","first-page":"410","article-title":"V-measure: A conditional entropy-based external cluster evaluation measure","volume-title":"Proc. Joint Conf. Empir. Methods Natural Lang. Process. Comput. Natural Lang. Learn.","author":"Rosenberg"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2931673"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref117","article-title":"The festival speech synthesis system, version 1.4.2","author":"Black","year":"2001"},{"key":"ref118","article-title":"Adam: Amethod for stochastic optimization","author":"Kingma"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-36"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2017.8273610"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053581"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/394083"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2074"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1097\/00001648-199209000-00012"},{"key":"ref130","article-title":"What is a p-value","author":"Thisted","year":"1998"},{"key":"ref131","first-page":"57","article-title":"Personality, perceptual, and cognitive correlates of emotional sensitivity","volume-title":"The Communication of Emotional Meaning","author":"Davitz","year":"1964"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195169157.003.0016"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1001\/archpsyc.1986.01800030098011"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-68"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(02)00084-5"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"issue":"4","key":"ref138","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1023\/A:1023237014909","article-title":"Emotion in speech: The acoustic attributes of fear, anger, sadness, and joy","volume":"28","author":"Sobin","year":"1999","journal-title":"J. Psycholinguistic Res."}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10056372\/09778970.pdf?arnumber=9778970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T23:13:36Z","timestamp":1705965216000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9778970\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":137,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2022.3175578","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}