{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T10:06:14Z","timestamp":1758189974967,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2020AAA0107901"],"award-info":[{"award-number":["2020AAA0107901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61961043"],"award-info":[{"award-number":["61961043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1109\/ialp68296.2024.11156500","type":"proceedings-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:32:18Z","timestamp":1758043938000},"page":"260-265","source":"Crossref","is-referenced-by-count":0,"title":["Emotional Speech Synthesis Based on Gated-Style Tokens and A Rhythm Predictor"],"prefix":"10.1109","author":[{"given":"Simiao","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Science &#x0026; Engineering, Yunnan University,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science &#x0026; Engineering, Yunnan University,Kunming,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A review-based study on different Text-to-Speech technologies","author":"Chowdhury","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1317"},{"key":"ref3","article-title":"Dex-tts: Diffusion-based expressive text-to-speech with style modeling on time variability","author":"Park","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Emotional end-to-end neural speech synthesizer","author":"Younggun","year":"2017","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Exploring transfer learning for low resource emotional tts","volume-title":"Intelligent Systems and Applications: Proceedings of the 2019 Intelligent Systems Conference (IntelliSys)","volume":"1","author":"No\u00e9","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095623"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8795-1_18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096710"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1322312"},{"key":"ref10","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","volume-title":"CoRR","volume":"abs\/2407.05407","author":"Du","year":"2024"},{"key":"ref11","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International conference on machine learning","author":"Popov","year":"2021"},{"key":"ref12","first-page":"164","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"Wang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang","year":"2018"},{"issue":"5","key":"ref14","first-page":"56","article-title":"A survey of emotional speech synthesis[J]","volume":"10","author":"Shi","year":"2024","journal-title":"Big Data Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-022-02126-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref17","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein","year":"2015"},{"key":"ref18","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning.","author":"Jaehyeon","year":"2021"},{"key":"ref20","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Jungil","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref22","article-title":"Emotion2Vec: Self-supervised pre-training for speech emotion representation","author":"Ma","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 International Conference on Asian Language Processing (IALP)","start":{"date-parts":[[2025,8,3]]},"location":"Sarawak, Malaysia","end":{"date-parts":[[2025,8,6]]}},"container-title":["2025 International Conference on Asian Language Processing (IALP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11156192\/11156242\/11156500.pdf?arnumber=11156500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T05:11:35Z","timestamp":1758085895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11156500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/ialp68296.2024.11156500","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]}}}