{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:13:02Z","timestamp":1774419182208,"version":"3.50.1"},"reference-count":34,"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"}],"funder":[{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10888185","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["VoiceGuider: Enhancing Out-of-Domain Performance in Parameter-Efficient Speaker-Adaptive Text-to-Speech via Autoguidance"],"prefix":"10.1109","author":[{"given":"Jiheum","family":"Yeom","sequence":"first","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Heeseung","family":"Kim","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Jooyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Che Hyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Nohil","family":"Park","sequence":"additional","affiliation":[{"name":"Seoul National University,Electrical and Computer Engineering,Seoul,Republic of Korea"}]},{"given":"Sungroh","family":"Yoon","sequence":"additional","affiliation":[{"name":"Seoul National University,ECE, AIIS, ASRI, INMC, ISRC, and IPAI,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the 32nd International Conference on Machine Learning","volume":"37","author":"Sohl-Dickstein"},{"key":"ref2","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ho","year":"2020"},{"key":"ref3","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref4","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref5","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref6","first-page":"32211","article-title":"Consistency models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Song"},{"key":"ref7","first-page":"8599","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"International Conference on Machine Learning","author":"Popov"},{"key":"ref8","first-page":"11119","article-title":"Guided-TTS: A diffusion model for text-to-speech via classifier guidance","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Kim"},{"key":"ref9","article-title":"Guided-tts 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim","year":"2022"},{"key":"ref10","first-page":"2709","article-title":"YourTTS: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Casanova"},{"key":"ref11","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref12","article-title":"P-flow: A fast and data-efficient zero-shot TTS through speech prompting","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Kim"},{"key":"ref13","article-title":"Naturalspeech 2: Latent diffusion models are natural and zero-shot speech and singing synthesizers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Shen"},{"key":"ref14","article-title":"Voicebox: Text-guided multilingual universal speech generation at scale","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Le"},{"key":"ref15","article-title":"Adaspeech: Adaptive text to speech for custom voice","volume-title":"International Conference on Learning Representations","author":"Chen"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414872"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2313"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2326"},{"key":"ref19","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-63"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref22","article-title":"The lj speech dataset","author":"Ito","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref24","article-title":"Guiding a diffusion model with a bad version of itself","author":"Karras","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1965"},{"key":"ref26","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref27","article-title":"Applying guidance in a limited interval improves sample and distribution quality in diffusion models","author":"Kynk\u00e4\u00e4nniemi","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref30","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"Kuchaiev","year":"2019"},{"key":"ref31","article-title":"Resemblyzer","author":"Louppe","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2016"},{"key":"ref33","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024"},{"key":"ref34","article-title":"BigV-GAN: A universal neural vocoder with large-scale training","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gil Lee"}],"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\/10888185.pdf?arnumber=10888185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:10Z","timestamp":1774416070000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10888185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10888185","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}