{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T14:25:07Z","timestamp":1774448707049,"version":"3.50.1"},"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\/icassp40776.2020.9054528","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T20:21:13Z","timestamp":1586463673000},"page":"7539-7543","source":"Crossref","is-referenced-by-count":13,"title":["AV(SE)<sup>2<\/sup>: Audio-Visual Squeeze-Excite Speech Enhancement"],"prefix":"10.1109","author":[{"given":"Michael L.","family":"Iuzzolino","sequence":"first","affiliation":[]},{"given":"Kazuhito","family":"Koishida","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2459017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref13","article-title":"cgans with projection discriminator","author":"miyato","year":"2018"},{"key":"ref14","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"hu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref15","article-title":"Sound event detection in multichannel audio using convolutional timefrequency-channel squeeze and excitation","author":"xia","year":"2019"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with lstms for lipreading","author":"stafylakis","year":"2017"},{"key":"ref17","article-title":"Visual speech enhancement","author":"gabbay","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682790"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"2067","DOI":"10.1109\/TASL.2010.2041110","article-title":"A tandem algorithm for pitch estimation and voiced speech segregation","volume":"18","author":"hu","year":"2010","journal-title":"IEEE Transactions on Audio Speech and Language Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2002.2012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.283.5406.1272"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00451"},{"key":"ref29","article-title":"Perceptual evaluation of speech quality (pesq): An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs","author":"recommendation","year":"2001","journal-title":"ITU-T Rec P 862"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00359"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speakerindependent audio-visual model for speech separation","author":"ephrat","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/423937a"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3114"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref20","first-page":"192","article-title":"S3fd: Single shot scale-invariant face detector","author":"zhang","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2012.10.004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28551-6_5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2016.10.005"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"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\/09054528.pdf?arnumber=9054528","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:23:54Z","timestamp":1656375834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9054528\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9054528","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}