{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T16:35:39Z","timestamp":1788280539653,"version":"build-2803163510"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956638","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T14:34:13Z","timestamp":1669732453000},"page":"663-669","source":"Crossref","is-referenced-by-count":13,"title":["U-Former: Improving Monaural Speech Enhancement with Multi-head Self and Cross Attention"],"prefix":"10.1109","author":[{"given":"Xinmeng","family":"Xu","sequence":"first","affiliation":[{"name":"Trinity College Dublin,E.E. Engineering,Dublin,Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Hao","sequence":"additional","affiliation":[{"name":"Hubei University of Chinese Medicine,School of Foreign Languages,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1155\/2010\/962103"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2291240"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.383638"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00572"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462417"},{"key":"ref12","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"bai","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053591"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref15","article-title":"Transformers in vision: A survey","author":"khan","year":"2021"},{"key":"ref16","article-title":"End-to-end multi-channel speech separation","author":"gu","year":"2019"},{"key":"ref17","first-page":"3816","article-title":"Joint time-frequency and time domain learning for speech enhancement","author":"tang","year":"2021","journal-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","first-page":"108","article-title":"Axial-deeplab: Stand-alone axial-attention for panoptic segmentation","author":"wang","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"ref28","article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","author":"stoller","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2270369"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413740"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/b14529"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-130"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2782"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1465"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163086"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/1.4986931"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref20","article-title":"Axial attention in multidimensional transformers","author":"ho","year":"2019"},{"key":"ref22","first-page":"1","article-title":"Demand: a collection of multichannel recordings of acoustic noise in diverse environments","author":"thiemann","year":"2013","journal-title":"Proc Meetings Acoust"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-1684(01)00128-1"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054536"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414569"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937186"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956638.pdf?arnumber=9956638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T13:52:02Z","timestamp":1698328322000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956638","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}