{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T16:23:07Z","timestamp":1761582187673},"reference-count":22,"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\/icassp43922.2022.9746762","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"source":"Crossref","is-referenced-by-count":8,"title":["Audio-Visual Wake Word Spotting System for MISP Challenge 2021"],"prefix":"10.1109","author":[{"given":"Yanguang","family":"Xu","sequence":"first","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Jianwei","family":"Sun","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Yang","family":"Han","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Shuaijiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Chaoyang","family":"Mei","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Tingwei","family":"Guo","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Shuran","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Chuandong","family":"Xie","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Wei","family":"Zou","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]},{"given":"Xiangang","family":"Li","sequence":"additional","affiliation":[{"name":"Beike,Beijing,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1560"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414097"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907840"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2520091"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451096"},{"key":"ref19","article-title":"Seeing wake words: Audio-visual keyword spotting","author":"momeni","year":"2020","journal-title":"arXiv preprint arXiv 2009 02026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004005"},{"key":"ref3","article-title":"Temporal feedback convolutional recurrent neural networks for keyword spotting","author":"kim","year":"2019","journal-title":"arXiv preprint arXiv 1911 01258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref5","article-title":"Attention-based end-to-end models for small-footprint key-word spotting","author":"shan","year":"2018","journal-title":"arXiv preprint arXiv 1803 10916"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-592"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2128"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134087"},{"key":"ref1","article-title":"Target speaker extraction for customizable query-by-example keyword spotting","author":"shao","year":"2021","journal-title":"APSIPA ASC"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-37"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746683"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref21","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"wu","year":"2020","journal-title":"arXiv preprint arXiv 2006 04989"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"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\/09746762.pdf?arnumber=9746762","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:29Z","timestamp":1660594229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746762\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746762","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}