{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T07:59:19Z","timestamp":1764403159807,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746808","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4743-4747","source":"Crossref","is-referenced-by-count":9,"title":["Residual-Guided Personalized Speech Synthesis based on Face Image"],"prefix":"10.1109","author":[{"given":"Jianrong","family":"Wang","sequence":"first","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaosheng","family":"Hu","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuewei","family":"Li","sequence":"additional","affiliation":[{"name":"Tianjin University,College of Intelligence and Computing,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Fang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Social Sciences,Institute of Linguistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"the Chinese University of Hong Kong,Shenzhen Research Institute of Big Data,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.2015EDP7457"},{"key":"ref11","first-page":"4879","article-title":"Generalized end-to-end loss for speaker verification","author":"li","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref12","first-page":"2410","article-title":"Efficient neural audio synthesis","volume":"80","author":"kalchbrenner","year":"2018","journal-title":"Proc ICML"},{"key":"ref13","first-page":"3","article-title":"Cbam: Convolutional block attention module","author":"woo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2014.2359646"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref4","first-page":"4485","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","author":"jia","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2434"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00772"},{"key":"ref5","first-page":"214","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"2018","journal-title":"Proc ICLR"},{"article-title":"Audio-driven talking face video generation with learning-based personalized head pose","year":"2020","author":"yi","key":"ref8"},{"article-title":"Attention-based residual speech portrait model for speech to face generation","year":"2020","author":"wang","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2136"},{"key":"ref1","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc Inter-speech 2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref22","article-title":"P. 800: Methods for subjective determination of transmission quality","volume":"22","author":"rec","year":"1996","journal-title":"International Telecommunication Union"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746808.pdf?arnumber=9746808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:45Z","timestamp":1660593945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746808","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}