{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:37:04Z","timestamp":1780447024683,"version":"3.54.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and communications Technology Planning & Evaluation"},{"name":"Korea government","award":["2019-0-00079"],"award-info":[{"award-number":["2019-0-00079"]}]},{"name":"Artificial Intelligence Graduate School Program","award":["2021-0-02068"],"award-info":[{"award-number":["2021-0-02068"]}]},{"name":"Artificial Intelligence Innovation Hub"},{"name":"Artificial Intelligence Convergence Innovation Human Resources Development and Voice&Avatar, Naver Cloud, Seongnam, Korea","award":["IITP-2024-RS-2023-00255968"],"award-info":[{"award-number":["IITP-2024-RS-2023-00255968"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3395994","type":"journal-article","created":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T17:32:47Z","timestamp":1714584767000},"page":"2654-2666","source":"Crossref","is-referenced-by-count":22,"title":["DiffProsody: Diffusion-Based Latent Prosody Generation for Expressive Speech Synthesis With Prosody Conditional Adversarial Training"],"prefix":"10.1109","volume":"32","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, Seoul, 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, Ajou University, Suwon-si, 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, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref2","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ren","year":"2019"},{"key":"ref3","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":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref5","first-page":"13963","article-title":"PortaSpeech: Portable and high-quality generative text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3156757"},{"key":"ref8","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Skerry-Ryan","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414102"},{"key":"ref10","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Wang","year":"2018"},{"key":"ref11","first-page":"7748","article-title":"Meta-StyleSpeech : Multi-speaker adaptive text-to-speech generation","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Min","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747388"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3169634"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-411"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-55"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-715"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746253"},{"key":"ref19","article-title":"AdaSpeech: Adaptive text to speech for custom voice","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3202126"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133205"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10116"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11133"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-379"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-47634-1_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref30","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia","year":"2022"},{"key":"ref31","first-page":"8599","article-title":"Grad-TTS: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Popov","year":"2021"},{"key":"ref32","first-page":"4328","article-title":"Diffusion-LM improves controllable text generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref36","article-title":"Attention is All you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref37","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","year":"2020"},{"key":"ref38","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":"ref39","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.","volume":"35","author":"Lee","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref41","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xiao","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145297"},{"key":"ref43","article-title":"PITS: Variational pitch inference without fundamental frequency for end-to-end pitch-controllable TTS","author":"Lee","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-925"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref46","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref49","article-title":"Neural Discrete Representation Learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Oord","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref52","first-page":"125","article-title":"WaveNet: A generative model for raw audio","volume-title":"Proc. 9th ISCA Speech Synth. Workshop","author":"Oord","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref54","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref55","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":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-126"},{"key":"ref57","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","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2892235"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2960721"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref61","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref64","article-title":"HiddenSinger: High-quality singing voice synthesis via neural audio codec and latent diffusion models","author":"Hwang","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747098"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10517426.pdf?arnumber=10517426","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T04:51:35Z","timestamp":1716007895000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10517426\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3395994","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}