{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:34:57Z","timestamp":1730230497124,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8682275","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T20:01:56Z","timestamp":1555531316000},"page":"7140-7144","source":"Crossref","is-referenced-by-count":4,"title":["Cross-language Speech Dependent Lip-synchronization"],"prefix":"10.1109","author":[{"given":"Abhishek","family":"Jha","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikram","family":"Voleti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinay","family":"Namboodiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref12","article-title":"End-to-end learning for 3d facial animation from raw waveforms of speech","author":"pham","year":"2017","journal-title":"arXiv preprint arXiv 1710 00920"},{"key":"ref13","article-title":"You said that?","author":"chung","year":"2017","journal-title":"arXiv preprint arXiv 1705 02966"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"article-title":"Obamanet: Photo-realistic lip-sync from text","year":"0","author":"kumar","key":"ref15"},{"key":"ref16","article-title":"You said that?","author":"chung","year":"2017","journal-title":"BMVC"},{"key":"ref17","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Image-to-image translation with conditional adversarial networks","author":"isola","year":"2016","journal-title":"arXiv preprint arXiv 1611 07004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00888"},{"key":"ref4","first-page":"252","article-title":"Visual vowel and diphthong perception across speakers","volume":"14","author":"kricos","year":"1981","journal-title":"J Acad Rehabilitative Audiology"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1044\/jshr.2803.381"},{"key":"ref6","article-title":"Lip reading sentences in the wild","author":"chung","year":"2016","journal-title":"CVPR"},{"year":"0","key":"ref5","article-title":"Machine Learning Course, Andrew Ng"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00023"},{"key":"ref7","article-title":"Combining residual networks with LSTMs for lipreading","author":"stafylakis","year":"2017","journal-title":"arXiv preprint arXiv 1703 06870"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref20","first-page":"5","article-title":"Framewise phoneme classification with bidirectional lstm and other neural network architectures","author":"graves","year":"2005","journal-title":"Neural Networks"},{"key":"ref22","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"JMLR"},{"year":"0","key":"ref21","article-title":"WEBRTC, VAD"},{"article-title":"Keras","year":"2015","author":"chollet","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref25","article-title":"Adam: A method for stochastic optimization","volume":"abs 1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2019,5,12]]},"location":"Brighton, United Kingdom","end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08682275.pdf?arnumber=8682275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T03:21:44Z","timestamp":1657855304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8682275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8682275","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}