{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T21:16:00Z","timestamp":1765228560988,"version":"3.46.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LQN25F020001"],"award-info":[{"award-number":["LQN25F020001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Staring Foundation of Hangzhou Institute for Advanced Study","award":["2024HIAS-C2001"],"award-info":[{"award-number":["2024HIAS-C2001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72271166"],"award-info":[{"award-number":["72271166"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cross-Modal Learning Project"},{"DOI":"10.13039\/100014815","name":"German Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014815","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2025.3534822","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T13:39:13Z","timestamp":1740404353000},"page":"15043-15054","source":"Crossref","is-referenced-by-count":2,"title":["Disentanglement of Prosody Representations via Diffusion Models and Scheduled Gradient Reversal"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6694-5355","authenticated-orcid":false,"given":"Leyuan","family":"Qu","sequence":"first","affiliation":[{"name":"Hangzhou Institute for Advanced Study, UCAS, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5163-938X","authenticated-orcid":false,"given":"Cornelius","family":"Weber","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"International Cultural Exchange College, Xinjiang University, Ürümqi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Business and Management, Shanghai International Studies University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5881-3723","authenticated-orcid":false,"given":"Yingming","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taihao","family":"Li","sequence":"additional","affiliation":[{"name":"Hangzhou Institute for Advanced Study, UCAS, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1343-4775","authenticated-orcid":false,"given":"Stefan","family":"Wermter","sequence":"additional","affiliation":[{"name":"Department of Informatics, University of Hamburg, Hamburg, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2478\/jagi-2014-0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2001-150"},{"volume-title":"Natural Language Understanding","year":"1995","author":"Allen","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref5","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref6","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref7","first-page":"16251","article-title":"Neural analysis and synthesis: Reconstructing speech from self-supervised representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Choi"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362098"},{"key":"ref9","first-page":"245","article-title":"The production of prosody","volume-title":"Language Production","author":"Cutler","year":"1980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbtep.2009.11.008"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2867099"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-571"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"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"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145293"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref19","first-page":"1","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446191"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3190715"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.085"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054580"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832278"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref28","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref29","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-647"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref35","article-title":"Deep speaker: An end-to-end neural speaker embedding system","author":"Li","year":"2017","journal-title":"arXiv:1705.02304"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2006.04.003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533390"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-demo.1"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3320864"},{"key":"ref41","first-page":"1","article-title":"DiffWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. ICLR","author":"Kong"},{"key":"ref42","first-page":"290","article-title":"DiffGAN-TTS: High-fidelity and efficient text-to-speech with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2874155"},{"key":"ref46","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-6670(17)54869-7"},{"key":"ref48","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"issue":"11","key":"ref51","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1044\/2018_JSLHR-H-ASCC7-18-0166"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414006"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414880"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2822"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.vrih.2020.12.002"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235194"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096966"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446186"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref63","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Baevski"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3369726"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446974"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446812"},{"key":"ref68","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref69","first-page":"3123","article-title":"The distress analysis interview corpus of human and computer interviews","volume-title":"Proc. Int. Conf. Lang. Resources Eval.","author":"Gratch"},{"key":"ref70","article-title":"A topic-attentive transformer-based model for multimodal depression detection","author":"Guo","year":"2022","journal-title":"arXiv:2206.13256"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054323"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_1"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3087"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10901998.pdf?arnumber=10901998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:28Z","timestamp":1765219288000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10901998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":74,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3534822","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}