{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T04:22:31Z","timestamp":1784607751816,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China Joint Fund Key Project","award":["U2003207"],"award-info":[{"award-number":["U2003207"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902064"],"award-info":[{"award-number":["61902064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["1908085MF209"],"award-info":[{"award-number":["1908085MF209"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Frontier Technology Basic Research Project","award":["BK20192004"],"award-info":[{"award-number":["BK20192004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/taffc.2024.3412152","type":"journal-article","created":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T18:31:51Z","timestamp":1718130711000},"page":"68-82","source":"Crossref","is-referenced-by-count":5,"title":["Controllable Multi-Speaker Emotional Speech Synthesis With an Emotion Representation of High Generalization Capability"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2602-2910","authenticated-orcid":false,"given":"Junjie","family":"Zheng","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6509-5520","authenticated-orcid":false,"given":"Jian","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7764-5179","authenticated-orcid":false,"given":"Wenming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Child Development and Learning Science (Southeast University), Ministry of Education, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8553-8421","authenticated-orcid":false,"given":"Liang","family":"Tao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0173-1625","authenticated-orcid":false,"given":"Hon Keung","family":"Kwan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-150"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1007\/978-94-011-5730-8_7","volume-title":"An Introduction to Text-to-Speech Synthesis","volume":"3","author":"Dutoit","year":"1997"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref5","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref6","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020"},{"key":"ref7","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282282"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref10","article-title":"Emotional end-to-end neural speech synthesizer","author":"Lee","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023186"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2931673"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1201\/9781410615862-13"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282231"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413398"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP54964.2022.9778768"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-610"},{"key":"ref23","article-title":"Cross-speaker emotion transfer based on speaker condition layer normalization and semi-supervised training in text-to-speech","author":"Wu","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref25","first-page":"2917","article-title":"Style equalization: Unsupervised learning of controllable generative sequence models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2918"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054556"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1992-260"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-71"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-153"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1002\/0470845945.ch32"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2014-37"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref40","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref41","article-title":"Multi-reference tacotron by intercross training for style disentangling, transfer and control in speech synthesis","author":"Bian","year":"2019"},{"key":"ref42","article-title":"Neural photo editing with introspective adversarial networks","author":"Brock","year":"2016"},{"key":"ref43","first-page":"367","article-title":"Interconversion of emotions in speech using TD-PSOLA","volume-title":"Proc. Symp. Signal Process. Intell. Recognit. Syst.","author":"Akanksh"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-6987-0_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref46","first-page":"794","article-title":"Emotion-controllable speech synthesis using emotion soft labels and fine-grained prosody factors","volume-title":"Proc. Asia-Pacific Signal Inf. Process. Assoc. Annu. Summit Conf.","author":"Luo"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref48","article-title":"Introduction to speech processing","author":"B\u00e4ckstr\u00f6m","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref50","article-title":"Towards out-of-distribution generalization: A survey","author":"Shen","year":"2021"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref52","first-page":"5089","article-title":"End-to-end speech emotion recognition using deep neural networks","volume-title":"Proc. IEEE Int. Conf. Acoust Speech Signal Process.","author":"Tzirakis"},{"issue":"11","key":"ref53","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref55","article-title":"Generating expression in synthesized speech","author":"Cahn","year":"1989"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/10908445\/10553521.pdf?arnumber=10553521","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T18:35:55Z","timestamp":1741026955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10553521\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":55,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3412152","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}