{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T15:29:39Z","timestamp":1749569379238},"reference-count":24,"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\/icassp43922.2022.9747535","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"9251-9255","source":"Crossref","is-referenced-by-count":7,"title":["Channel-Wise AV-Fusion Attention for Multi-Channel Audio-Visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Gaopeng","family":"Xu","sequence":"first","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Yang","sequence":"additional","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guo","family":"Wei","sequence":"additional","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junfeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Gao","sequence":"additional","affiliation":[{"name":"NIO Co., Ltd."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1948"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref12","first-page":"1","article-title":"NARA-WPE: A python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing","author":"drude","year":"2018","journal-title":"Speech Communication 13th ITG-Symposium"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003785"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2346"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"article-title":"WeNet: Production First and Production Ready End-to-End Speech Recognition Toolkit[J]","year":"2021","author":"zhang","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2018-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682586"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref7","first-page":"2130","article-title":"Large-scale multilingual speech recognition with a streaming end-to-end model","author":"anjuli","year":"2019","journal-title":"Proc ISCA Interspeech"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"article-title":"Multistream CNN for robust acoustic modeling","year":"2020","author":"han","key":"ref9"},{"key":"ref20","first-page":"1","article-title":"NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing[C]","author":"drude","year":"2018","journal-title":"Speech Communication 13th ITG-Symposium"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-655"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"}],"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\/09747535.pdf?arnumber=9747535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:11:17Z","timestamp":1660594277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747535","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}