{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:28:29Z","timestamp":1774420109903,"version":"3.50.1"},"reference-count":37,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","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\/icassp49660.2025.10889904","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":2,"title":["Fine-portraitist: Visualizing the Speaker\u2019s Face Portrait during Speech Listening"],"prefix":"10.1109","author":[{"given":"Jinting","family":"Wang","sequence":"first","affiliation":[{"name":"HKUST (GZ),Artificial Intelligence,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"HKUST (GZ),Artificial Intelligence,Guangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab Tencent,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682970"},{"key":"ref2","article-title":"Face reconstruction from voice using generative adversarial networks","volume":"32","author":"Wen","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1358"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095994"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746808"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1118"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472707"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34694"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414260"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1814"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01723"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-340"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611779"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPICS58376.2023.10235541"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02074-w"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547850"},{"key":"ref23","article-title":"From inference to generation: End-to-end fully self-supervised generation of human face from speech","author":"Choi","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Realistic speech-to-face generation with speech-conditioned latent diffusion model with face prior","author":"Wang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.19080\/GJO.2019.20.556041"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532682"},{"key":"ref29","article-title":"Lift yourself up: Retrieval-augmented text generation with self-memory","volume":"36","author":"Cheng","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447898"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref32","article-title":"From inference to generation: End-to-end fully self-supervised generation of human face from speech","volume-title":"International Conference on Learning Representations","author":"Choi"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref35","article-title":"Deep convolutional neural network for age estimation based on vgg-face model","author":"Qawaqneh","year":"2017"},{"issue":"3","key":"ref36","first-page":"404","article-title":"Content based image retrieval: survey","volume":"19","author":"Rehman","year":"2012","journal-title":"World Applied Sciences Journal"},{"key":"ref37","first-page":"24266","article-title":"Retrievalguard: Provably robust 1-nearest neighbor image retrieval","volume-title":"International Conference on Machine Learning","author":"Wu"}],"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\/10889904.pdf?arnumber=10889904","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:26Z","timestamp":1774416386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889904\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889904","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}