{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:35:29Z","timestamp":1730230529093,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9054005","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"581-585","source":"Crossref","is-referenced-by-count":4,"title":["A Dynamic Stream Weight Backprop Kalman Filter for Audiovisual Speaker Tracking"],"prefix":"10.1109","author":[{"given":"Christopher","family":"Schymura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tsubasa","family":"Ochiai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keisuke","family":"Kinoshita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Nakatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Araki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1109\/TASL.2012.2183869"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TASL.2006.881678"},{"key":"ref11","first-page":"1","article-title":"2D audio-visual localization in home environments using a particle filter","author":"gerlach","year":"2012","journal-title":"10 ITG Symposium on Speech Communication"},{"key":"ref12","first-page":"4376","article-title":"Backprop KF: Learning discriminative deterministic state estimators","volume":"29","author":"haarnoja","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Recurrent kalman networks: Factorized inference in high-dimensional deep feature spaces","volume":"abs 1905 7357","author":"becker","year":"2019","journal-title":"CoRR"},{"key":"ref14","first-page":"2746","article-title":"Embed to control: A locally linear latent dynamics model for control from raw images","volume":"28","author":"watter","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"3601","article-title":"A disentangled recognition and nonlinear dynamics model for unsupervised learning","volume":"30","author":"fraccaro","year":"2017","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1162\/neco.1997.9.8.1735"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.3115\/v1\/W14-4012"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/IWAENC.2018.8521384"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR.2014.241"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TPAMI.2011.47"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICASSP.2018.8461310"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ICASSP.2018.8461326"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TPAMI.2017.2648793"},{"year":"2014","author":"kingma","journal-title":"Adam A method for stochastic optimization","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/ICASSP.2015.7178882"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/SLT.2016.7846282"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/WIW.2016.043"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TASLP.2017.2783545"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ASPAA.2005.1540183"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref20","first-page":"i","article-title":"Frame-dependent multi-stream reliability indicators for audio-visual speech recognition","author":"garg","year":"2003","journal-title":"2003 IEEE International Conference on Acoustics Speech and Signal Processing 2003 Proceedings (ICASSP ’03)"},{"key":"ref22","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"International Conference on Learning Representations ICLR 2015"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICIP.2008.4712005"},{"year":"2017","author":"veaux","journal-title":"CSTR VCTK corpus English multi-speaker corpus for cstr voice cloning toolkit","key":"ref24"},{"key":"ref23","article-title":"Audiovisual speaker tracking using nonlinear dynamical systems with dynamic stream weights","volume":"abs 1903 6031","author":"schymura","year":"2019","journal-title":"CoRR"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/LSP.2010.2091502"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1109\/TMM.2015.2428998"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2020,5,4]]},"location":"Barcelona, Spain","end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09054005.pdf?arnumber=9054005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:24:35Z","timestamp":1656375875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054005","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}