{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T21:04:53Z","timestamp":1780434293006,"version":"3.54.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371144"],"award-info":[{"award-number":["62371144"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62461004"],"award-info":[{"award-number":["62461004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172458"],"award-info":[{"award-number":["62172458"]}],"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":[[2026,4]]},"DOI":"10.1109\/taffc.2026.3654113","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:40:42Z","timestamp":1768423242000},"page":"1652-1662","source":"Crossref","is-referenced-by-count":0,"title":["Emo-DiT: Emotional Speech Synthesis With a Diffusion Model Approach to Enhance Naturalness and Emotional Expressiveness"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7250-681X","authenticated-orcid":false,"given":"Yao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3489-1887","authenticated-orcid":false,"given":"Lina","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1222-1249","authenticated-orcid":false,"given":"Bingzhen","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9918-5783","authenticated-orcid":false,"given":"Jinhong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7751-6200","authenticated-orcid":false,"given":"Dongnan","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9508-5006","authenticated-orcid":false,"given":"Miao","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information, Guangxi University, Nanning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6887-130X","authenticated-orcid":false,"given":"Yuan Yan","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2023.3250266"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1148"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref4","article-title":"MM-TTS: A unified framework for multimodal, prompt-induced emotional text-to-speech synthesis","author":"Li","year":"2024","journal-title":"CoRR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref8","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Cof. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref9","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref10","first-page":"22605","article-title":"NaturalSpeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","volume-title":"Proc. 41st Int. Conf. on Mach. Learn.","author":"Ju","year":"2024"},{"key":"ref11","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-534"},{"key":"ref13","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-17"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095621"},{"key":"ref16","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","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref21","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref22","first-page":"2672","article-title":"Generative Adversarial Nets.","volume-title":"NIPS","author":"Goodfellow","year":"2014"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00482"},{"key":"ref24","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hoogeboom","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00692"},{"key":"ref26","first-page":"25702","article-title":"Latent diffusion energy-based model for interpretable text modelling","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01372"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00686"},{"key":"ref31","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2021"},{"key":"ref32","first-page":"4263","article-title":"Parallel sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Proces. Syst.","volume":"36","author":"Shih","year":"2023"},{"key":"ref33","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref34","article-title":"Score-Based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00663"},{"key":"ref36","article-title":"Fast sampling of diffusion models with exponential integrator","volume-title":"NeurIPS 2022 Workshop on Score-Based Methods","author":"Zhang","year":"2022"},{"key":"ref37","article-title":"A survey on neural speech synthesis","author":"Tan","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402088"},{"key":"ref39","article-title":"Classifier-Free diffusion guidance","volume-title":"Proc. NeurIPS Workshop Deep Generative Models Downstream Appl.","author":"Ho","year":"2021"},{"key":"ref40","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol","year":"2022"},{"key":"ref41","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00654"},{"key":"ref44","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref47","article-title":"The emotional voices database: Towards controlling the emotion dimension in voice generation systems","author":"Adigwe","year":"2018"},{"key":"ref48","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.","volume":"33","author":"Kong","year":"2020"},{"key":"ref49","first-page":"19594","article-title":"StyleTTS 2: Towards human-level text-to-speech through style diffusion and adversarial training with large speech language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832320"},{"key":"ref52","article-title":"DEX-TTS: Diffusion-based expressive text-to-speech with style modeling on time variability","author":"Park","year":"2024"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11540045\/11352958.pdf?arnumber=11352958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:07:40Z","timestamp":1780430860000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11352958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":52,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2026.3654113","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}