{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:00:52Z","timestamp":1764403252776},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094745","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"source":"Crossref","is-referenced-by-count":17,"title":["Imaginary Voice: Face-Styled Diffusion Model for Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Jiyoung","family":"Lee","sequence":"first","affiliation":[{"name":"NAVER AI Lab,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon","family":"Son Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soo-Whan","family":"Chung","sequence":"additional","affiliation":[{"name":"NAVER Cloud,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-301"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref12","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"2020","journal-title":"ICLRE"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746808"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref36","article-title":"Nsml: Meet the mlaas platform with a real-world case study","author":"kim","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref30","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"ICLRE"},{"key":"ref11","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","author":"popov","year":"2021","journal-title":"ICML"},{"key":"ref33","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref10","article-title":"Guided-tts 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"kim","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref1","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"ref19","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref23","article-title":"Face-filter: Audio-visual speech separation using still images","author":"chung","year":"2020","journal-title":"InterSpeech"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987720"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-1045-8"},{"key":"ref21","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"nichol","year":"2022","journal-title":"ICML"},{"key":"ref28","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref27","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2021","journal-title":"ICLRE"},{"key":"ref29","article-title":"Fitting new speakers based on a short untranscribed sample","author":"nachmani","year":"2018","journal-title":"ICML"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref7","article-title":"Hierarchical text-conditional image generation with clip latents","author":"ramesh","year":"2022"},{"key":"ref9","article-title":"Guided-tts: A diffusion model for text-to-speech via classifier guidance","author":"kim","year":"2022","journal-title":"ICML"},{"key":"ref4","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"2015","journal-title":"ICML"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"InterSpeech"},{"key":"ref6","article-title":"Diffusion models beat gans on image synthesis","author":"dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094745.pdf?arnumber=10094745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:25Z","timestamp":1700507365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094745","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}