{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:38:55Z","timestamp":1780357135741,"version":"3.54.1"},"reference-count":25,"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\/icassp49660.2025.10890553","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting"],"prefix":"10.1109","author":[{"given":"Wooseok","family":"Han","sequence":"first","affiliation":[{"name":"AITRICS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minki","family":"Kang","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changhun","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST, AITRICS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunho","family":"Yang","sequence":"additional","affiliation":[{"name":"KAIST, AITRICS"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","volume-title":"International Conference on Learning Representations (ICLR)","author":"Shen"},{"key":"ref2","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref4","article-title":"Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias","author":"Jiang","year":"2023"},{"key":"ref5","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone","volume-title":"International Conference on Machine Learning (ICML)","author":"Casanova"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref7","article-title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref8","article-title":"Adapting TTS models For New Speakers using Transfer Learning","author":"Neekhara","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref12","article-title":"Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speech","volume-title":"International Conference on Machine Learning (ICML)","author":"Popov"},{"key":"ref13","article-title":"Fast-Speech: Fast, Robust and Controllable Text to Speech","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ren"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref15","article-title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","volume-title":"International Conference on Machine Learning (ICML)","author":"Min"},{"key":"ref16","article-title":"Neural Discrete Representation Learning","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"van den Oord"},{"key":"ref17","article-title":"Denoising Diffusion Probabilistic Models","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Ho"},{"key":"ref18","article-title":"Score-Based Generative Modeling through Stochastic Differential Equations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Song"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref20","article-title":"Language Models are Unsupervised Multitask Learners","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref21","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","volume-title":"Tech. Rep.","author":"Yamagishi","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref23","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford"},{"key":"ref24","article-title":"Resemblyzer","year":"2020"},{"key":"ref25","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Kong"}],"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\/10890553.pdf?arnumber=10890553","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:53Z","timestamp":1774416173000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890553\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890553","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}