{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:25Z","timestamp":1774419505026,"version":"3.50.1"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889756","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Improving Robustness of Diffusion-Based Zero-Shot Speech Synthesis via Stable Formant Generation"],"prefix":"10.1109","author":[{"given":"Changjin","family":"Han","sequence":"first","affiliation":[{"name":"DeepBrain AI,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seokgi","family":"Lee","sequence":"additional","affiliation":[{"name":"DeepBrain AI,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gyuhyeon","family":"Nam","sequence":"additional","affiliation":[{"name":"DeepBrain AI,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gyeongsu","family":"Chae","sequence":"additional","affiliation":[{"name":"DeepBrain AI,Seoul,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"ICML","author":"Sohl-Dickstein"},{"key":"ref2","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song"},{"key":"ref4","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","author":"Popov","year":"2021","journal-title":"ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref6","article-title":"Wavegrad: Estimating gradients for waveform generation","volume-title":"ICLR","author":"Chen"},{"key":"ref7","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref8","author":"Chen","year":"2022","journal-title":"Resgrad: Residual denoising diffusion probabilistic models for text to speech"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10096710"},{"key":"ref11","article-title":"Generspeech: Towards style transfer for generalizable out-of-domain text-to-speech","author":"Huang","year":"2022","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Yourtts: Towards zero-shot multi-speaker tts and zero-shot voice conversion for everyone","volume-title":"ICML","author":"Casanova"},{"key":"ref13","author":"Wang","year":"2023","journal-title":"Neural codec language models are zero-shot text to speech synthesizers"},{"key":"ref14","article-title":"Mega-tts 2: Boosting prompting mechanisms for zero-shot speech synthesis","volume-title":"ICLR","author":"Jiang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-25"},{"key":"ref16","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"ICLR","author":"Shen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref18","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref20","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"ICLR","author":"Ren"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref22","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"ICML","author":"Min"},{"key":"ref23","volume-title":"The vowel: Its nature and structure","author":"Chiba","year":"1941"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1515\/9783110873429"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/acrefore\/9780199384655.013.894"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-866"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icassp39728.2021.9413889"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref31","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (ver-sion 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1774"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03958"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1006\/jsvi.1998.2072"},{"key":"ref35","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","volume-title":"ICLR","author":"Popov"},{"key":"ref36","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NeurIPS","author":"Kong","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097255"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688047"},{"key":"ref40","author":"Lyth","year":"2024","journal-title":"Natural language guidance of high-fidelity text-to-speech with synthetic annotations"},{"key":"ref41","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095751"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1599"},{"key":"ref44","article-title":"Common voice: A massively-multilingual speech corpus","volume-title":"LREC","author":"Ardila"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref46","volume-title":"Better speech synthesis through scaling","author":"Betker","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.673"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889756.pdf?arnumber=10889756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:12Z","timestamp":1774416192000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889756","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}