{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:38:24Z","timestamp":1761896304597,"version":"3.28.0"},"reference-count":10,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/sii.2015.7404961","type":"proceedings-article","created":{"date-parts":[[2016,3,25]],"date-time":"2016-03-25T18:22:17Z","timestamp":1458930137000},"page":"100-105","source":"Crossref","is-referenced-by-count":15,"title":["Talking heads synthesis from audio with deep neural networks"],"prefix":"10.1109","author":[{"given":"Taiki","family":"Shimba","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryuhei","family":"Sakurai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hirotake","family":"Yamazoe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo-Ho","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","first-page":"2667","article-title":"Photo-Realistic Expressive Text to Talking Head Synthesis","author":"vincent","year":"2013","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654890"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1986.1164788"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-61520-919-4.ch017"},{"key":"ref8","first-page":"101","article-title":"Speech Emotion Recognition Using Support Vector Machine","volume":"2","author":"pan","year":"2012","journal-title":"International Journal of Smart Home"},{"key":"ref7","article-title":"Emotion Recognition by Speech Signals","author":"kwon","year":"2003","journal-title":"InterSpeech"},{"key":"ref2","first-page":"322","article-title":"Phoneme-to-viseme Mapping for Visual Speech Recognition","author":"cappelletta","year":"2012","journal-title":"ICPRAM"},{"article-title":"Facial Action Coding System","year":"1978","author":"ekman","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CA.1998.681914"}],"event":{"name":"2015 IEEE\/SICE International Symposium on System Integration (SII)","start":{"date-parts":[[2015,12,11]]},"location":"Nagoya, Japan","end":{"date-parts":[[2015,12,13]]}},"container-title":["2015 IEEE\/SICE International Symposium on System Integration (SII)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397479\/7404874\/07404961.pdf?arnumber=7404961","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T18:45:19Z","timestamp":1490208319000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404961\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/sii.2015.7404961","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}