{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T05:26:01Z","timestamp":1755926761577,"version":"3.28.0"},"reference-count":20,"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\/icassp49357.2023.10095084","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":2,"title":["Visual-Aware Text-to-Speech<sup>*<\/sup>"],"prefix":"10.1109","author":[{"given":"Mohan","family":"Zhou","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Yalong","family":"Bai","sequence":"additional","affiliation":[{"name":"JD Explore Academy,Beijing,China"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD Explore Academy,Beijing,China"}]},{"given":"Ting","family":"Yao","sequence":"additional","affiliation":[{"name":"JD Explore Academy,Beijing,China"}]},{"given":"Tiejun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}]},{"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"JD Explore Academy,Beijing,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2009.58"},{"key":"ref12","first-page":"413","article-title":"Facewarehouse: A 3d facial expression database for visual computing","volume":"20","author":"cao","year":"2013","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383317"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960497"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00038"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1995189"},{"article-title":"Vico-x: Multimodal conversation dataset","year":"2022","author":"zhou","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5121\/ijcsea.2012.2410"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref8","article-title":"The jddc corpus: A large-scale multi-turn chinese dialogue dataset for e-commerce customer service","author":"chen","year":"2019","journal-title":"arXiv preprint arXiv 1911 09070"},{"article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","year":"2019","author":"yamagishi","key":"ref7"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref3","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"arXiv preprint arXiv 1703 10593"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref6"},{"key":"ref5","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095084.pdf?arnumber=10095084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:00:32Z","timestamp":1699902032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095084","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}