{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:40:05Z","timestamp":1783183205364,"version":"3.54.6"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation"},{"name":"Korea government","award":["RS-2019-II190079"],"award-info":[{"award-number":["RS-2019-II190079"]}]},{"name":"Artificial Intelligence Graduate School Program"},{"name":"Artificial Intelligence Innovation Hub","award":["RS-2021-II-212068"],"award-info":[{"award-number":["RS-2021-II-212068"]}]},{"name":"Artificial Intelligence Convergence Innovation Human Resources Development","award":["IITP-2024-RS-2023-00255968"],"award-info":[{"award-number":["IITP-2024-RS-2023-00255968"]}]},{"name":"AI Technology for Interactive Communication of Language Impaired Individuals","award":["RS-2024-00336673"],"award-info":[{"award-number":["RS-2024-00336673"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/taffc.2025.3530920","type":"journal-article","created":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T13:37:27Z","timestamp":1737121047000},"page":"1660-1674","source":"Crossref","is-referenced-by-count":13,"title":["DurFlex-EVC: Duration-Flexible Emotional Voice Conversion Leveraging Discrete Representations Without Text Alignment"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7229-8123","authenticated-orcid":false,"given":"Hyung-Seok","family":"Oh","sequence":"first","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8925-4474","authenticated-orcid":false,"given":"Sang-Hoon","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Software and Computer Engineering, Department of Artificial Intelligence, Ajou University, Suwon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4673-9882","authenticated-orcid":false,"given":"Deok-Hyeon","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-4996","authenticated-orcid":false,"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seongbuk-gu, South Korea"}],"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":"10.1109\/TAFFC.2022.3190233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2763134"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3211694"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.14"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1053"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687906"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2878"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383526"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1647"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr40276.2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.299"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683865"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053255"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-781"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3175578"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref24","first-page":"3171","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref25","first-page":"1","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.769"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref30","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref31","first-page":"1","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baevski"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref34","first-page":"18003","article-title":"ContentVec: An improved self-supervised speech representation by disentangling speakers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1608"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747814"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref39","first-page":"1","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref40","article-title":"UniAudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"},{"key":"ref41","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref42","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref45","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":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683282"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413973"},{"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.","author":"Kong"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref50","first-page":"1","article-title":"DifWave: A versatile diffusion model for audio synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kong"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639647"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10636"},{"key":"ref55","first-page":"10970","article-title":"GenerSpeech: Towards style transfer for generalizable out-of-domain text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref56","article-title":"AdaSpeech: Adaptive text to speech for custom voice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref58","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"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref60","first-page":"1","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Gil Lee"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-60"},{"key":"ref64","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.931"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3233324"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1990"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3164181"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268571"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref71","first-page":"16624","article-title":"HierSpeech: Bridging the gap between text and speech by hierarchical variational inference using self-supervised representations for speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref73","first-page":"7748","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Min"},{"key":"ref74","first-page":"1180","article-title":"Unsupervised domain adaptation by backpropagation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ganin"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2828429"},{"key":"ref76","first-page":"1","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3395994"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17559"},{"key":"ref79","first-page":"294","article-title":"Voicemixer: Adversarial voice style mixup","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3349053"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447331"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003829"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383524"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053732"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447981"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11152495\/10844546.pdf?arnumber=10844546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T05:59:29Z","timestamp":1757138369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10844546\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":86,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3530920","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}