{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:10:59Z","timestamp":1764400259899,"version":"3.46.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249151","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"1116-1121","source":"Crossref","is-referenced-by-count":0,"title":["Face-Conditioned Large-Scale Text-to-Speech via Speaker Embedding Prediction from Facial Images"],"prefix":"10.1109","author":[{"given":"Umi","family":"Okamoto","sequence":"first","affiliation":[{"name":"Nagoya Institute of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sei","family":"Ueno","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akinobu","family":"Lee","sequence":"additional","affiliation":[{"name":"Nagoya Institute of Technology,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/ICASSP49357.2023.10095515"},{"key":"ref2","article-title":"Mega-tts: Zero-shot text-to-speech at scale with intrinsic inductive bias","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref4","article-title":"Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Naturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models","author":"Ju","year":"2024","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.21437\/Interspeech.2020-2136"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP43922.2022.9746808"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP49357.2023.10094745"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ICASSP49660.2025.10889667"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.21437\/Interspeech.2025-47"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref12","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"International conference on machine learning","author":"Wang","year":"2018"},{"key":"ref13","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.21437\/Interspeech.2020-2826"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref19","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref20","first-page":"49205","article-title":"Symbolic discovery of optimization algorithms","volume":"36","author":"Chen","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref22","first-page":"17 022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"Kong","year":"2020","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICASSP.2015.7178964"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.21437\/Interspeech.2020-3015"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249151.pdf?arnumber=11249151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:06:09Z","timestamp":1764399969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249151","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}