{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:47:06Z","timestamp":1778604426719,"version":"3.51.4"},"reference-count":24,"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\/icassp49357.2023.10095515","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":29,"title":["Grad-StyleSpeech: Any-Speaker Adaptive Text-to-Speech Synthesis with Diffusion Models"],"prefix":"10.1109","author":[{"given":"Minki","family":"Kang","sequence":"first","affiliation":[{"name":"AITRICS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongchan","family":"Min","sequence":"additional","affiliation":[{"name":"AITRICS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung Ju","family":"Hwang","sequence":"additional","affiliation":[{"name":"AITRICS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Sample efficient adaptive text-to-speech","author":"chen","year":"2019","journal-title":"ICLR 2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref12","first-page":"10040","article-title":"Neural voice cloning with a few samples","author":"arik","year":"2018","journal-title":"NeurIPS 2018"},{"key":"ref23","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","author":"popov","year":"2022","journal-title":"ICLRE"},{"key":"ref15","article-title":"Meta-stylespeech : Multi-speaker adaptive text-to-speech generation","author":"min","year":"2021","journal-title":"ICML"},{"key":"ref14","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref22","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"yamagishi","year":"2019"},{"key":"ref10","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for endto-end text-to-speech","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref2","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","author":"kim","year":"2020","journal-title":"NeurIPS"},{"key":"ref1","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NeurIPS 2017"},{"key":"ref17","article-title":"Yourtts: Towards zero-shot multi-speaker TTS and zero-shot voice conversion for everyone","author":"casanova","year":"2022","journal-title":"ICML"},{"key":"ref16","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"chen","year":"2021","journal-title":"ICLR 2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.564"},{"key":"ref8","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","author":"popov","year":"2021","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-469"},{"key":"ref9","first-page":"11119","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":"Hifigan: Generative adversarial networks for efficient and high fidelity speech synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"ICLRE"},{"key":"ref6","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"2021","journal-title":"ICLRE"},{"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\/10095515.pdf?arnumber=10095515","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:11:04Z","timestamp":1700507464000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095515\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095515","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}