{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:45:08Z","timestamp":1729626308531,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,11]]},"DOI":"10.1109\/iscslp.2010.5684834","type":"proceedings-article","created":{"date-parts":[[2011,1,10]],"date-time":"2011-01-10T21:16:26Z","timestamp":1294694186000},"page":"129-134","source":"Crossref","is-referenced-by-count":2,"title":["Rendering a personalized photo-real talking head from short video footage"],"prefix":"10.1109","author":[{"given":"Lijuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojun","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank K.","family":"Soong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1145\/280814.280825"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1145\/311535.311556"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1145\/1201775.882269"},{"key":"ref30","article-title":"Fast Normalized Cross-Correlation","author":"lewis","year":"0","journal-title":"Industrial Light & Magic"},{"year":"0","journal-title":"Video demonstration of our synthesis results","key":"ref34"},{"key":"ref10","first-page":"2034","article-title":"HMM-based unit selection using frame sized speech segments","author":"ling","year":"2006","journal-title":"Proc Interspeech 2006"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/ICASSP.2010.5495150"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"2310","DOI":"10.21437\/Interspeech.2008-590","article-title":"LIPS2008: Visual Speech Synthesis Challenge","author":"theobald","year":"2008","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/79.911195"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TVCG.2005.43"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CA.1998.681914"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/CA.1998.681913"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/j.specom.2004.07.002"},{"key":"ref18","first-page":"461","article-title":"Parameterization of Mouth Images by LLE and PCA for Image-Based Facial Animation","volume":"v","author":"liu","year":"2006","journal-title":"Proc ICASSP 2006"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/TCSVT.2006.885727"},{"key":"ref28","first-page":"37","article-title":"Using 5 ms segments in concatenative speech synthesis","author":"hirai","year":"2004","journal-title":"Proc of 5th ISCA Speech Synthesis Workshop"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1145\/566654.566594","article-title":"Trainable video realistic speech animation","author":"ezzat","year":"2002","journal-title":"Proc ACM SIGGRAPH2002"},{"key":"ref27","first-page":"1703","article-title":"The IBM trainable speech synthesis system","author":"donovan","year":"1998","journal-title":"Proc ICSLP"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP.2002.5745033"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2330","DOI":"10.21437\/Interspeech.2008-594","article-title":"Realistic Facial Animation System for Interactive Services","author":"liu","year":"2008","journal-title":"Proc INTERSPEECH"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/ICASSP.1996.541110"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-540-85853-9_12"},{"key":"ref8","article-title":"HMM-based Text-To-Audio-Visual Speech Synthesis","author":"sako","year":"2000","journal-title":"ICSLP"},{"year":"0","author":"tokuda","article-title":"The HMM-based speech synthesis system (HTS)","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1145\/258734.258880"},{"key":"ref9","first-page":"1128","article-title":"Speech Animation Using Coupled Hidden Markov Models","author":"xie","year":"2006","journal-title":"Proc of ICPR'06"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/6046.865480"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/TNN.2002.1021886"},{"key":"ref22","first-page":"389","article-title":"Speech synthesis using HMMs with dynamic features","volume":"i","author":"tokuda","year":"1996","journal-title":"Proc ICASSP"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TMM.2005.846777"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/ICASSP.2005.1415037"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/ICASSP.1999.758104"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/ICASSP.1997.596097"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1145\/1201775.882269"}],"event":{"name":"2010 7th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2010,11,29]]},"location":"Tainan, Taiwan","end":{"date-parts":[[2010,12,3]]}},"container-title":["2010 7th International Symposium on Chinese Spoken Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5677866\/5684476\/05684834.pdf?arnumber=5684834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T04:30:40Z","timestamp":1637123440000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5684834\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,11]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2010.5684834","relation":{},"subject":[],"published":{"date-parts":[[2010,11]]}}}