{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T22:30:29Z","timestamp":1781217029524,"version":"3.54.1"},"reference-count":71,"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":"National Key Research and Development Program of China","award":["2020AAA0108600"],"award-info":[{"award-number":["2020AAA0108600"]}]}],"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.2023.3313413","type":"journal-article","created":{"date-parts":[[2023,9,8]],"date-time":"2023-09-08T17:38:56Z","timestamp":1694194736000},"page":"3418-3430","source":"Crossref","is-referenced-by-count":21,"title":["DiCLET-TTS: Diffusion Model Based Cross-Lingual Emotion Transfer for Text-to-Speech \u2014 A Study Between English and Mandarin"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5578-3960","authenticated-orcid":false,"given":"Tao","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Cong","sequence":"additional","affiliation":[{"name":"Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinfa","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6284-5979","authenticated-orcid":false,"given":"Jingbei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech, Audio, and Music Intelligence Group, ByteDance, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2668"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1244"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101427"},{"key":"ref4","first-page":"16582","article-title":"Neural dubber: Dubbing for videos according to scripts","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hu","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10639-019-10009-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2070"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1265"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746914"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-205"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053094"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1163"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682674"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2654"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-327"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2679"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"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":"10.1109\/itc-cscc.2019.8793393"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref22","first-page":"2966","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Ark","year":"2017"},{"key":"ref23","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref24","article-title":"Multi-reference Tacotron by intercross training for style disentangling, transfer and control in speech synthesis","author":"Bian","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2985"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-610"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/3588190"},{"issue":"4","key":"ref29","first-page":"891","article-title":"Tone and non-tone languages: An alternative to language typology and parameters","volume":"5","author":"Duanmu","year":"2004","journal-title":"Lang. Linguistics"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-21430-x"},{"key":"ref31","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein","year":"2015"},{"key":"ref32","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref33","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Song","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref35","first-page":"23593","article-title":"Denoising diffusion restoration models","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Kawar","year":"2022"},{"key":"ref36","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":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1897"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/577"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01211"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1464"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1632"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-979"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP57327.2022.10038056"},{"key":"ref46","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":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268571"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362069"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-534"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2024.3361474\/mm1"},{"key":"ref54","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref55","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Popov","year":"2021"},{"key":"ref56","first-page":"23689","article-title":"Binauralgrad: A two-stage conditional diffusion probabilistic model for binaural audio synthesis","author":"Leng","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3268730"},{"key":"ref59","article-title":"Priorgrad: Improving conditional denoising diffusion models with data-dependent adaptive prior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lee","year":"2021"},{"key":"ref60","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref61","article-title":"Guided-TTS 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-960"},{"key":"ref64","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":"ref65","article-title":"Adaspeech: Adaptive text to speech for custom voice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2020"},{"key":"ref66","article-title":"DelightfulTTS: The microsoft speech synthesis system for blizzard challenge","author":"Liu","year":"2021"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref69","first-page":"17022","article-title":"Hifi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"issue":"2605","key":"ref71","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Laurens","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10244091.pdf?arnumber=10244091","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:02:09Z","timestamp":1710403329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10244091\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3313413","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}