{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:42:58Z","timestamp":1767339778050},"reference-count":20,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747559","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8042-8046","source":"Crossref","is-referenced-by-count":3,"title":["Learning to Predict Speech in Silent Videos Via Audiovisual Analogy"],"prefix":"10.1109","author":[{"given":"Ravindra","family":"Yadav","sequence":"first","affiliation":[{"name":"Indian Institute of Technology Kanpur,India"}]},{"given":"Ashish","family":"Sardana","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Vinay P","family":"Namboodiri","sequence":"additional","affiliation":[{"name":"University of Bath,UK"}]},{"given":"Rajesh M","family":"Hegde","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology Kanpur,India"}]}],"member":"263","reference":[{"key":"ref10","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1445"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01381"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Speech prediction in silent videos using variational autoencoders","year":"2020","author":"yadav","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref16","first-page":"1252","article-title":"Deep visual analogy-making","author":"reed","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2716178"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953127"},{"key":"ref5","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461856"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.61"},{"key":"ref2","article-title":"Unsupervised representation learning by predicting image rotations","author":"spyros gidaris","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref1","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"jacob devlin","year":"0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"}],"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\/09747559.pdf?arnumber=9747559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:09:28Z","timestamp":1660594168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747559","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}