{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:20:19Z","timestamp":1780636819811,"version":"3.54.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Alibaba Group through Alibaba Research Intern Program"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021RC244"],"award-info":[{"award-number":["2021RC244"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3268571","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T21:14:55Z","timestamp":1682025295000},"page":"1693-1705","source":"Crossref","is-referenced-by-count":27,"title":["iEmoTTS: Toward Robust Cross-Speaker Emotion Transfer and Control for Speech Synthesis Based on Disentanglement Between Prosody and Timbre"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8640-8933","authenticated-orcid":false,"given":"Guangyan","family":"Zhang","sequence":"first","affiliation":[{"name":"Intelligent Connectivity, Cloud & Technology, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4606-7174","authenticated-orcid":false,"given":"Ying","family":"Qin","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intelligent Connectivity, Cloud & Technology, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialun","family":"Wu","sequence":"additional","affiliation":[{"name":"Intelligent Connectivity, Cloud & Technology, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Li","sequence":"additional","affiliation":[{"name":"Intelligent Connectivity, Cloud & Technology, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1464-5478","authenticated-orcid":false,"given":"Yutao","family":"Gai","sequence":"additional","affiliation":[{"name":"Intelligent Connectivity, Cloud & Technology, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feijun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Intelligent Connectivity, Cloud & Technology, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7089-3436","authenticated-orcid":false,"given":"Tan","family":"Lee","sequence":"additional","affiliation":[{"name":"DSP & Speech Technology Laboratory, Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511816338"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref8","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iscslp49672.2021.9362098"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.502"},{"key":"ref12","article-title":"Emotional end-to-end neural speech synthesizer","volume-title":"Proc. Adv. Neural Inf. Process. Syst. Neural Inf. Process. Syst. Found.","author":"Lee","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295x.97.3.315"},{"key":"ref16","first-page":"2966","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gibiansky","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref18","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref19","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","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1049"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref22","volume-title":"American National Standard Psychoacoustical Terminology","year":"1973"},{"key":"ref23","first-page":"7836","article-title":"Unsupervised speech decomposition via triple information bottleneck","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1854"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref27","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":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref29","first-page":"159","article-title":"Towards speaking style transplantation in speech synthesis","volume-title":"Proc. 8th ISCA Workshop Speech Synth.","author":"Lorenzo-Trueba","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-116"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282231"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2385478"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2075"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2985"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3069"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref37","first-page":"861","article-title":"Multi-reference tacotron by intercross training for style disentangling, transfer and control in speech synthesis","volume-title":"Proc. Interspeech","author":"Bian","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1446"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413398"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-979"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10131"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.005"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref44","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":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref46","first-page":"5210","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-200"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref52","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref55","first-page":"5","article-title":"Categorical reparameterization with gumbel-softmax","volume":"1050","author":"Jang","year":"2017","journal-title":"Stat"},{"key":"ref56","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maddison","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746425"},{"key":"ref58","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref59","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":"ref60","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19551-8_23"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1002\/9781444395068"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10106091.pdf?arnumber=10106091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T03:20:33Z","timestamp":1709263233000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10106091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3268571","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}