{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T16:49:56Z","timestamp":1767977396090,"version":"3.49.0"},"reference-count":25,"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\/icassp43922.2022.9747204","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"251-255","source":"Crossref","is-referenced-by-count":3,"title":["Speaker-Targeted Audio-Visual Speech Recognition Using a Hybrid CTC\/Attention Model with Interference Loss"],"prefix":"10.1109","author":[{"given":"Ryota","family":"Tsunoda","sequence":"first","affiliation":[{"name":"Kobe University,Graduate School of System Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryo","family":"Aihara","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Corporation,Information Technology R&D Center,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ryoichi","family":"Takashima","sequence":"additional","affiliation":[{"name":"Kobe University,Graduate School of System Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tetsuya","family":"Takiguchi","sequence":"additional","affiliation":[{"name":"Kobe University,Graduate School of System Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshie","family":"Imai","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Corporation,Information Technology R&D Center,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref12","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume":"32","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref13","article-title":"End-to-end continuous speech recognition using attention-based recurrent NN: First results","author":"chorowski","year":"2014","journal-title":"Proc NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-595"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref17","article-title":"Algorithms to measure audio programme loudness and true-peak audio level","year":"2012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref4","first-page":"484","article-title":"Audio-visual speech recognition in noisy audio environments","author":"pale?ek","year":"2013","journal-title":"Proc TSP"},{"key":"ref3","first-page":"1","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243014"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2980436"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1038\/264746a0","article-title":"Hearing lips and seeing voices","volume":"264","author":"mcgurk","year":"1976","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref22","article-title":"ADADELTA: An adaptive learning rate method","volume":"abs 1212 5701","author":"zeiler","year":"2012","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref24","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1513"}],"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\/09747204.pdf?arnumber=9747204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:05:45Z","timestamp":1660593945000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747204","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}