{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:50:16Z","timestamp":1772905816930,"version":"3.50.1"},"reference-count":35,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746683","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"9266-9270","source":"Crossref","is-referenced-by-count":40,"title":["The First Multimodal Information Based Speech Processing (Misp) Challenge: Data, Tasks, Baselines And Results"],"prefix":"10.1109","author":[{"given":"Hang","family":"Chen","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Hengshun","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,China"}]},{"given":"Chin-Hui","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,USA"}]},{"given":"Jingdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,China"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}]},{"given":"Sabato Marco","family":"Siniscalchi","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology,USA"}]},{"given":"Odette","family":"Scharenborg","sequence":"additional","affiliation":[{"name":"Delft University of Technology,The Netherlands"}]},{"given":"Di-Yuan","family":"Liu","sequence":"additional","affiliation":[{"name":"iFlytek,China"}]},{"given":"Bao-Cai","family":"Yin","sequence":"additional","affiliation":[{"name":"iFlytek,China"}]},{"given":"Jia","family":"Pan","sequence":"additional","affiliation":[{"name":"iFlytek,China"}]},{"given":"Jian-Qing","family":"Gao","sequence":"additional","affiliation":[{"name":"iFlytek,China"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"iFlytek,China"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Srilm–an extensible language modeling toolkit","author":"stolcke","year":"2004","journal-title":"Proc ICSLP 2002"},{"key":"ref32","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"IEEE Signal Processing Society"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.902460"},{"key":"ref30","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":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2007.4430116"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1198793"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688126"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/CHiME.2020-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907229"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICSLP.1996.607895"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3109\/03005368709077786"},{"key":"ref18","author":"massaro","year":"2014","journal-title":"Speech Perception by Ear and Eye A Paradigm for Psychological Inquiry"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8721.2008.00615.x"},{"key":"ref28","article-title":"Seeing wake words: Audio-visual keyword spotting","author":"momeni","year":"2020","journal-title":"BMVA"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3036783"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-552"},{"key":"ref6","author":"li","year":"2015","journal-title":"Robust Automatic Speech Recognition A Bridge to Practical Applications"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/9781118392683"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637622"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471664"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-010-9116-x"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472671"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.06.003"},{"key":"ref22","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc ACCV 2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref24","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"afouras","year":"2018","journal-title":"arXiv preprint arXiv 1809 00496"},{"key":"ref23","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383546"},{"key":"ref25","first-page":"112:1","article-title":"Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation","author":"ephrat","year":"2018","journal-title":"ACM Trans Graph"}],"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\/09746683.pdf?arnumber=9746683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:49Z","timestamp":1660593949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746683","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}