{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:18:12Z","timestamp":1774419492312,"version":"3.50.1"},"reference-count":24,"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\/icassp49660.2025.10889667","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":1,"title":["Face-StyleSpeech: Enhancing Zero-shot Speech Synthesis from Face Images with Improved Face-to-Speech Mapping"],"prefix":"10.1109","author":[{"given":"Minki","family":"Kang","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wooseok","family":"Han","sequence":"additional","affiliation":[{"name":"AITRICS"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunho","family":"Yang","sequence":"additional","affiliation":[{"name":"KAIST, AITRICS"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural voice cloning with a few samples","volume-title":"NeurIPS","author":"Arik"},{"key":"ref2","article-title":"Meta-stylespeech: Multi-speaker adaptive text-to-speech generation","volume-title":"ICML","author":"Min"},{"key":"ref3","article-title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone","volume-title":"ICML","author":"Casanova"},{"key":"ref4","article-title":"Guided-tts 2: A diffusion model for high-quality adaptive text-to-speech with untranscribed data","author":"Kim"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP49357.2023.10095515","article-title":"Grad-stylespeech: Any-speaker adaptive text-to-speech synthesis with diffusion models","volume-title":"ICASSP 2023","author":"Kang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2136"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746808"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094745"},{"key":"ref9","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-901"},{"key":"ref13","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"ICLR","author":"Ren"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref15","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref16","article-title":"Neural discrete representation learning","volume-title":"NeurIPS","author":"van den Oord"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746883"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref19","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NeurIPS","author":"Kong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref21","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"ICML","author":"Popov"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.518"},{"key":"ref24","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"ICML","author":"Radford"}],"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\/10889667.pdf?arnumber=10889667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:08Z","timestamp":1774416188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889667","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}